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

Dataset: Open Web Text

Neuron 2590 in Layer 2

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: 1.7481. Min Range: -1.7481

Max Act: 1.7481. Min Act: -0.1700

Data Index: 5706811 (Open Web Text)

Max Activating Token Index: 680

Text #1

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6922. Min Act: -0.1698

Data Index: 2602726 (Open Web Text)

Max Activating Token Index: 423

Text #2

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6627. Min Act: -0.1699

Data Index: 2204787 (Open Web Text)

Max Activating Token Index: 513

Text #3

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6436. Min Act: -0.1700

Data Index: 3585201 (Open Web Text)

Max Activating Token Index: 953

Text #4

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6355. Min Act: -0.1699

Data Index: 7227453 (Open Web Text)

Max Activating Token Index: 864

Text #5

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6463. Min Act: -0.1700

Data Index: 3770944 (Open Web Text)

Max Activating Token Index: 173

Text #6

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6405. Min Act: -0.1697

Data Index: 6474997 (Open Web Text)

Max Activating Token Index: 795

Text #7

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6235. Min Act: -0.1700

Data Index: 6023927 (Open Web Text)

Max Activating Token Index: 420

Text #8

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6227. Min Act: -0.1683

Data Index: 6548172 (Open Web Text)

Max Activating Token Index: 371

Text #9

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6226. Min Act: -0.1696

Data Index: 6467448 (Open Web Text)

Max Activating Token Index: 148

Text #10

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6145. Min Act: -0.1700

Data Index: 2957952 (Open Web Text)

Max Activating Token Index: 949

Text #11

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6186. Min Act: -0.1678

Data Index: 1822113 (Open Web Text)

Max Activating Token Index: 711

Text #12

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6132. Min Act: -0.1700

Data Index: 604041 (Open Web Text)

Max Activating Token Index: 165

Text #13

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6081. Min Act: -0.1699

Data Index: 6063712 (Open Web Text)

Max Activating Token Index: 640

Text #14

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6056. Min Act: -0.1700

Data Index: 5615392 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.5953. Min Act: -0.1700

Data Index: 6142980 (Open Web Text)

Max Activating Token Index: 193

Text #16

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6007. Min Act: -0.1700

Data Index: 2005716 (Open Web Text)

Max Activating Token Index: 382

Text #17

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.6113. Min Act: -0.1700

Data Index: 4299495 (Open Web Text)

Max Activating Token Index: 619

Text #18

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.5877. Min Act: -0.1700

Data Index: 7052951 (Open Web Text)

Max Activating Token Index: 298

Text #19

Max Range: 1.7481. Min Range: -1.7481

Max Act: 1.5888. Min Act: -0.1700

Data Index: 661261 (Open Web Text)

Max Activating Token Index: 932