Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1969 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.9279. Min Act: -0.1576

Data Index: 3929264 (Open Web Text)

Max Activating Token Index: 295

Text #1

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.9260. Min Act: -0.1507

Data Index: 180702 (Open Web Text)

Max Activating Token Index: 885

Text #2

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.9163. Min Act: -0.1700

Data Index: 6807150 (Open Web Text)

Max Activating Token Index: 98

Text #3

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.9007. Min Act: -0.0947

Data Index: 650274 (Open Web Text)

Max Activating Token Index: 55

Text #4

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8872. Min Act: -0.1692

Data Index: 7830579 (Open Web Text)

Max Activating Token Index: 281

Text #5

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8846. Min Act: -0.1689

Data Index: 7252411 (Open Web Text)

Max Activating Token Index: 427

Text #6

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8674. Min Act: -0.1672

Data Index: 4359480 (Open Web Text)

Max Activating Token Index: 1015

Text #7

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8428. Min Act: -0.1500

Data Index: 6987635 (Open Web Text)

Max Activating Token Index: 696

Text #8

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8502. Min Act: -0.1688

Data Index: 8225266 (Open Web Text)

Max Activating Token Index: 524

Text #9

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8475. Min Act: -0.1630

Data Index: 718408 (Open Web Text)

Max Activating Token Index: 769

Text #10

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8407. Min Act: -0.1670

Data Index: 5555614 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8409. Min Act: -0.1678

Data Index: 1816559 (Open Web Text)

Max Activating Token Index: 394

Text #12

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8428. Min Act: -0.1619

Data Index: 5705655 (Open Web Text)

Max Activating Token Index: 1019

Text #13

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8292. Min Act: -0.1446

Data Index: 587732 (Open Web Text)

Max Activating Token Index: 696

Text #14

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8348. Min Act: -0.1589

Data Index: 1822676 (Open Web Text)

Max Activating Token Index: 281

Text #15

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8251. Min Act: -0.1666

Data Index: 6305323 (Open Web Text)

Max Activating Token Index: 555

Text #16

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8332. Min Act: -0.1470

Data Index: 6153172 (Open Web Text)

Max Activating Token Index: 238

Text #17

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8319. Min Act: -0.1589

Data Index: 6052150 (Open Web Text)

Max Activating Token Index: 106

Text #18

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8184. Min Act: -0.1653

Data Index: 7571211 (Open Web Text)

Max Activating Token Index: 992

Text #19

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8430. Min Act: -0.1610

Data Index: 475935 (Open Web Text)

Max Activating Token Index: 483