< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 10 in Layer 38

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.9177. Min Act: -0.1699

Data Index: 3386465 (Open Web Text)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.3552. Min Act: -0.1700

Data Index: 5779095 (Open Web Text)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.2927. Min Act: -0.1700

Data Index: 2196315 (Open Web Text)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.2614. Min Act: -0.1700

Data Index: 6983599 (Open Web Text)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.2302. Min Act: -0.1700

Data Index: 1398747 (Open Web Text)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.2302. Min Act: -0.1697

Data Index: 1116367 (Open Web Text)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.2302. Min Act: -0.1700

Data Index: 7065704 (Open Web Text)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.2302. Min Act: -0.1700

Data Index: 5861060 (Open Web Text)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1989. Min Act: -0.1700

Data Index: 4793112 (Open Web Text)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1989. Min Act: -0.1700

Data Index: 2426935 (Open Web Text)

Max Activating Token Index: 90

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1677. Min Act: -0.1700

Data Index: 3282366 (Open Web Text)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1677. Min Act: -0.1700

Data Index: 8130245 (Open Web Text)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1677. Min Act: -0.1700

Data Index: 6983605 (Open Web Text)

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1989. Min Act: -0.1700

Data Index: 1985427 (Open Web Text)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1364. Min Act: -0.1700

Data Index: 3843582 (Open Web Text)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1052. Min Act: -0.1700

Data Index: 4338487 (Open Web Text)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1052. Min Act: -0.1700

Data Index: 1477313 (Open Web Text)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1052. Min Act: -0.1700

Data Index: 1795617 (Open Web Text)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1052. Min Act: -0.1700

Data Index: 5154258 (Open Web Text)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 7.9177. Min Range: -7.9177

Max Act: 7.1052. Min Act: -0.1700

Data Index: 2426937 (Open Web Text)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #19