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

Dataset: Open Web Text

Neuron 1056 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: 3.4346. Min Range: -3.4346

Max Act: 3.4346. Min Act: -0.1700

Data Index: 6007172 (Open Web Text)

Max Activating Token Index: 73

Text #1

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.4030. Min Act: -0.1700

Data Index: 698260 (Open Web Text)

Max Activating Token Index: 195

Text #2

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.3756. Min Act: -0.1700

Data Index: 6005261 (Open Web Text)

Max Activating Token Index: 903

Text #3

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.3837. Min Act: -0.1700

Data Index: 6069336 (Open Web Text)

Max Activating Token Index: 676

Text #4

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.3580. Min Act: -0.1700

Data Index: 81277 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2991. Min Act: -0.1700

Data Index: 6455721 (Open Web Text)

Max Activating Token Index: 509

Text #6

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.3097. Min Act: -0.1700

Data Index: 7842101 (Open Web Text)

Max Activating Token Index: 510

Text #7

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2830. Min Act: -0.1700

Data Index: 1354209 (Open Web Text)

Max Activating Token Index: 215

Text #8

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2833. Min Act: -0.1700

Data Index: 8653338 (Open Web Text)

Max Activating Token Index: 795

Text #9

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2656. Min Act: -0.1700

Data Index: 2838606 (Open Web Text)

Max Activating Token Index: 656

Text #10

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2910. Min Act: -0.1700

Data Index: 3648007 (Open Web Text)

Max Activating Token Index: 335

Text #11

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2572. Min Act: -0.1700

Data Index: 3626437 (Open Web Text)

Max Activating Token Index: 74

Text #12

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2674. Min Act: -0.1700

Data Index: 7478871 (Open Web Text)

Max Activating Token Index: 773

Text #13

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2812. Min Act: -0.1700

Data Index: 106727 (Open Web Text)

Max Activating Token Index: 372

Text #14

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2338. Min Act: -0.1700

Data Index: 8218572 (Open Web Text)

Max Activating Token Index: 601

Text #15

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2293. Min Act: -0.1700

Data Index: 3288133 (Open Web Text)

Max Activating Token Index: 567

Text #16

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2356. Min Act: -0.1700

Data Index: 3486861 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2507. Min Act: -0.1700

Data Index: 5229047 (Open Web Text)

Max Activating Token Index: 660

Text #18

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2267. Min Act: -0.1700

Data Index: 5927742 (Open Web Text)

Max Activating Token Index: 876

Text #19

Max Range: 3.4346. Min Range: -3.4346

Max Act: 3.2362. Min Act: -0.1700

Data Index: 55023 (Open Web Text)

Max Activating Token Index: 457