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

Dataset: Open Web Text

Neuron 601 in Layer 5

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: 6.6157. Min Range: -6.6157

Max Act: 6.6157. Min Act: -0.1700

Data Index: 3839998 (Open Web Text)

Max Activating Token Index: 760

Text #1

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.5300. Min Act: -0.1700

Data Index: 3022067 (Open Web Text)

Max Activating Token Index: 642

Text #2

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.3817. Min Act: -0.1700

Data Index: 659557 (Open Web Text)

Max Activating Token Index: 770

Text #3

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.3710. Min Act: -0.1700

Data Index: 1007982 (Open Web Text)

Max Activating Token Index: 611

Text #4

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.4119. Min Act: -0.1700

Data Index: 6034895 (Open Web Text)

Max Activating Token Index: 708

Text #5

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.3647. Min Act: -0.1700

Data Index: 4835018 (Open Web Text)

Max Activating Token Index: 744

Text #6

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.3578. Min Act: -0.1700

Data Index: 5864382 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.3453. Min Act: -0.1700

Data Index: 6227884 (Open Web Text)

Max Activating Token Index: 480

Text #8

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.3226. Min Act: -0.1700

Data Index: 5455362 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.2897. Min Act: -0.1700

Data Index: 5315910 (Open Web Text)

Max Activating Token Index: 331

Text #10

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.3250. Min Act: -0.1700

Data Index: 1345942 (Open Web Text)

Max Activating Token Index: 371

Text #11

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.3336. Min Act: -0.1700

Data Index: 7001986 (Open Web Text)

Max Activating Token Index: 390

Text #12

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.2689. Min Act: -0.1700

Data Index: 4611714 (Open Web Text)

Max Activating Token Index: 641

Text #13

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.3125. Min Act: -0.1700

Data Index: 2032612 (Open Web Text)

Max Activating Token Index: 501

Text #14

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.3117. Min Act: -0.1700

Data Index: 8598717 (Open Web Text)

Max Activating Token Index: 696

Text #15

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.2309. Min Act: -0.1700

Data Index: 1024285 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.2377. Min Act: -0.1700

Data Index: 8176506 (Open Web Text)

Max Activating Token Index: 312

Text #17

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.2423. Min Act: -0.1700

Data Index: 3782439 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.2843. Min Act: -0.1700

Data Index: 4670056 (Open Web Text)

Max Activating Token Index: 650

Text #19

Max Range: 6.6157. Min Range: -6.6157

Max Act: 6.2109. Min Act: -0.1700

Data Index: 7639208 (Open Web Text)

Max Activating Token Index: 497