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

Dataset: Open Web Text

Neuron 149 in Layer 4

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: 7.1216. Min Range: -7.1216

Max Act: 7.1216. Min Act: -0.1700

Data Index: 7365649 (Open Web Text)

Max Activating Token Index: 471

Text #1

Max Range: 7.1216. Min Range: -7.1216

Max Act: 7.0298. Min Act: -0.1700

Data Index: 1473235 (Open Web Text)

Max Activating Token Index: 60

Text #2

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9735. Min Act: -0.1700

Data Index: 6610331 (Open Web Text)

Max Activating Token Index: 686

Text #3

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9871. Min Act: -0.1700

Data Index: 8154153 (Open Web Text)

Max Activating Token Index: 563

Text #4

Max Range: 7.1216. Min Range: -7.1216

Max Act: 7.0225. Min Act: -0.1700

Data Index: 3436869 (Open Web Text)

Max Activating Token Index: 560

Text #5

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9482. Min Act: -0.1700

Data Index: 6492374 (Open Web Text)

Max Activating Token Index: 359

Text #6

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9517. Min Act: -0.1700

Data Index: 8516312 (Open Web Text)

Max Activating Token Index: 302

Text #7

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.8983. Min Act: -0.1700

Data Index: 4648082 (Open Web Text)

Max Activating Token Index: 398

Text #8

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9678. Min Act: -0.1700

Data Index: 519305 (Open Web Text)

Max Activating Token Index: 582

Text #9

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9144. Min Act: -0.1700

Data Index: 6005374 (Open Web Text)

Max Activating Token Index: 926

Text #10

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9138. Min Act: -0.1700

Data Index: 3488312 (Open Web Text)

Max Activating Token Index: 361

Text #11

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.8929. Min Act: -0.1700

Data Index: 1054710 (Open Web Text)

Max Activating Token Index: 361

Text #12

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9213. Min Act: -0.1700

Data Index: 8059889 (Open Web Text)

Max Activating Token Index: 343

Text #13

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9287. Min Act: -0.1700

Data Index: 3526327 (Open Web Text)

Max Activating Token Index: 67

Text #14

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9666. Min Act: -0.1699

Data Index: 2703852 (Open Web Text)

Max Activating Token Index: 985

Text #15

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.8920. Min Act: -0.1700

Data Index: 3613502 (Open Web Text)

Max Activating Token Index: 842

Text #16

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.8589. Min Act: -0.1700

Data Index: 5306130 (Open Web Text)

Max Activating Token Index: 419

Text #17

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9478. Min Act: -0.1700

Data Index: 5916972 (Open Web Text)

Max Activating Token Index: 573

Text #18

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9155. Min Act: -0.1698

Data Index: 617787 (Open Web Text)

Max Activating Token Index: 919

Text #19

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.8772. Min Act: -0.1700

Data Index: 2362378 (Open Web Text)

Max Activating Token Index: 442