< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6379 in Layer 46

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 13.6184. Min Range: -13.6184

Max Act: 13.6184. Min Act: -0.1700

Data Index: 8221370 (Open Web Text)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 13.6184. Min Range: -13.6184

Max Act: 13.2434. Min Act: -0.1700

Data Index: 4691452 (Open Web Text)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 13.6184. Min Range: -13.6184

Max Act: 13.0559. Min Act: -0.1700

Data Index: 5917933 (Open Web Text)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.9309. Min Act: -0.1700

Data Index: 2451679 (Open Web Text)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.8059. Min Act: -0.1700

Data Index: 5002743 (Open Web Text)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.7434. Min Act: -0.1700

Data Index: 8664302 (Open Web Text)

Max Activating Token Index: 706

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.6184. Min Act: -0.1700

Data Index: 8186418 (Open Web Text)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.6809. Min Act: -0.1700

Data Index: 3282263 (Open Web Text)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.5559. Min Act: -0.1700

Data Index: 1232276 (Open Web Text)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.4934. Min Act: -0.1700

Data Index: 4747524 (Open Web Text)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.4309. Min Act: -0.1700

Data Index: 8479636 (Open Web Text)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.4934. Min Act: -0.1700

Data Index: 5510227 (Open Web Text)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.3684. Min Act: -0.1700

Data Index: 8660498 (Open Web Text)

Max Activating Token Index: 583

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.3684. Min Act: -0.1700

Data Index: 1369559 (Open Web Text)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.3059. Min Act: -0.1700

Data Index: 8442095 (Open Web Text)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.3059. Min Act: -0.1700

Data Index: 2581553 (Open Web Text)

Max Activating Token Index: 947

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.3059. Min Act: -0.1700

Data Index: 381845 (Open Web Text)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.1809. Min Act: -0.1700

Data Index: 5565591 (Open Web Text)

Max Activating Token Index: 1008

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.2434. Min Act: -0.1700

Data Index: 6805309 (Open Web Text)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 13.6184. Min Range: -13.6184

Max Act: 12.1809. Min Act: -0.1700

Data Index: 1896710 (Open Web Text)

Max Activating Token Index: 79

Click toggle to see full text

Truncated

Full Text #19