< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 46 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 3.0242. Min Range: -3.0242

Max Act: 3.0242. Min Act: -0.1700

Data Index: 3493436 (The Pile)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.9768. Min Act: -0.1700

Data Index: 10028434 (The Pile)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.9610. Min Act: -0.1700

Data Index: 1960673 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.9293. Min Act: -0.1700

Data Index: 2206310 (The Pile)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.9135. Min Act: -0.1700

Data Index: 10249037 (The Pile)

Max Activating Token Index: 643

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8976. Min Act: -0.1700

Data Index: 2359460 (The Pile)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8976. Min Act: -0.1700

Data Index: 2983857 (The Pile)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8817. Min Act: -0.1700

Data Index: 2305706 (The Pile)

Max Activating Token Index: 981

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8817. Min Act: -0.1700

Data Index: 4738548 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8658. Min Act: -0.1700

Data Index: 717543 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8658. Min Act: -0.1700

Data Index: 10108475 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8500. Min Act: -0.1700

Data Index: 400287 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8500. Min Act: -0.1700

Data Index: 6276622 (The Pile)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8341. Min Act: -0.1700

Data Index: 7988768 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8341. Min Act: -0.1700

Data Index: 2389463 (The Pile)

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8341. Min Act: -0.1700

Data Index: 5695442 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8341. Min Act: -0.1700

Data Index: 5893330 (The Pile)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8341. Min Act: -0.1700

Data Index: 7495572 (The Pile)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8341. Min Act: -0.1700

Data Index: 4216984 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0242. Min Range: -3.0242

Max Act: 2.8341. Min Act: -0.1700

Data Index: 5599969 (The Pile)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #19