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

Dataset: Open Web Text

Neuron 2867 in Layer 6

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: 3.2401. Min Range: -3.2401

Max Act: 3.2401. Min Act: -0.1700

Data Index: 6398099 (Open Web Text)

Max Activating Token Index: 743

Text #1

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.2241. Min Act: -0.1700

Data Index: 4972322 (Open Web Text)

Max Activating Token Index: 265

Text #2

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.2117. Min Act: -0.1700

Data Index: 1620684 (Open Web Text)

Max Activating Token Index: 234

Text #3

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.1648. Min Act: -0.1700

Data Index: 7554419 (Open Web Text)

Max Activating Token Index: 566

Text #4

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.1009. Min Act: -0.1699

Data Index: 8439029 (Open Web Text)

Max Activating Token Index: 966

Text #5

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.1191. Min Act: -0.1700

Data Index: 8015115 (Open Web Text)

Max Activating Token Index: 204

Text #6

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0909. Min Act: -0.1700

Data Index: 4608356 (Open Web Text)

Max Activating Token Index: 902

Text #7

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0660. Min Act: -0.1700

Data Index: 6325585 (Open Web Text)

Max Activating Token Index: 662

Text #8

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0971. Min Act: -0.1700

Data Index: 8611478 (Open Web Text)

Max Activating Token Index: 623

Text #9

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0943. Min Act: -0.1700

Data Index: 5568178 (Open Web Text)

Max Activating Token Index: 668

Text #10

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0709. Min Act: -0.1700

Data Index: 43634 (Open Web Text)

Max Activating Token Index: 682

Text #11

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0306. Min Act: -0.1700

Data Index: 1527205 (Open Web Text)

Max Activating Token Index: 786

Text #12

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0292. Min Act: -0.1700

Data Index: 3135409 (Open Web Text)

Max Activating Token Index: 493

Text #13

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0107. Min Act: -0.1700

Data Index: 1432773 (Open Web Text)

Max Activating Token Index: 355

Text #14

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0062. Min Act: -0.1700

Data Index: 6773557 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0169. Min Act: -0.1700

Data Index: 2531762 (Open Web Text)

Max Activating Token Index: 902

Text #16

Max Range: 3.2401. Min Range: -3.2401

Max Act: 2.9849. Min Act: -0.1700

Data Index: 8698395 (Open Web Text)

Max Activating Token Index: 676

Text #17

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0120. Min Act: -0.1700

Data Index: 3845021 (Open Web Text)

Max Activating Token Index: 140

Text #18

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0075. Min Act: -0.1700

Data Index: 5935142 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 3.2401. Min Range: -3.2401

Max Act: 3.0159. Min Act: -0.1700

Data Index: 1300715 (Open Web Text)

Max Activating Token Index: 524