< Prev | Home | Model | Random | Next >

Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 4063 in Layer 20

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.8183. Min Act: -0.1700

Data Index: 1144250 (Open Web Text)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.7558. Min Act: -0.1700

Data Index: 5492077 (Open Web Text)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.6621. Min Act: -0.1700

Data Index: 4874738 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.6308. Min Act: -0.1700

Data Index: 2713554 (Open Web Text)

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.6308. Min Act: -0.1700

Data Index: 8332550 (Open Web Text)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.5058. Min Act: -0.1700

Data Index: 3355938 (Open Web Text)

Max Activating Token Index: 51

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.4121. Min Act: -0.1700

Data Index: 321493 (Open Web Text)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.4433. Min Act: -0.1700

Data Index: 8698335 (Open Web Text)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.4121. Min Act: -0.1700

Data Index: 5697532 (Open Web Text)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.4121. Min Act: -0.1700

Data Index: 502471 (Open Web Text)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.4433. Min Act: -0.1700

Data Index: 308916 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.3808. Min Act: -0.1700

Data Index: 321492 (Open Web Text)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.3496. Min Act: -0.1700

Data Index: 1964171 (Open Web Text)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.3808. Min Act: -0.1700

Data Index: 2661170 (Open Web Text)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.4121. Min Act: -0.1700

Data Index: 2166599 (Open Web Text)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.3496. Min Act: -0.1700

Data Index: 2377449 (Open Web Text)

Max Activating Token Index: 706

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.3496. Min Act: -0.1700

Data Index: 622676 (Open Web Text)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.2558. Min Act: -0.1700

Data Index: 6965895 (Open Web Text)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.3183. Min Act: -0.1700

Data Index: 8581025 (Open Web Text)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.8183. Min Range: -6.8183

Max Act: 6.3183. Min Act: -0.1700

Data Index: 7117743 (Open Web Text)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #19