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

Dataset: Open Web Text

Neuron 1226 in Layer 1

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: 1.3656. Min Range: -1.3656

Max Act: 1.3656. Min Act: -0.1700

Data Index: 6826887 (Open Web Text)

Max Activating Token Index: 716

Text #1

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3512. Min Act: -0.1700

Data Index: 2830440 (Open Web Text)

Max Activating Token Index: 959

Text #2

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3503. Min Act: -0.1700

Data Index: 1023842 (Open Web Text)

Max Activating Token Index: 1020

Text #3

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3478. Min Act: -0.1700

Data Index: 4243166 (Open Web Text)

Max Activating Token Index: 517

Text #4

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3469. Min Act: -0.1700

Data Index: 1109908 (Open Web Text)

Max Activating Token Index: 605

Text #5

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3381. Min Act: -0.1700

Data Index: 7777060 (Open Web Text)

Max Activating Token Index: 806

Text #6

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3452. Min Act: -0.1700

Data Index: 5058942 (Open Web Text)

Max Activating Token Index: 804

Text #7

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3487. Min Act: -0.1700

Data Index: 2334988 (Open Web Text)

Max Activating Token Index: 322

Text #8

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3385. Min Act: -0.1700

Data Index: 7327842 (Open Web Text)

Max Activating Token Index: 983

Text #9

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3294. Min Act: -0.1700

Data Index: 4397248 (Open Web Text)

Max Activating Token Index: 611

Text #10

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3281. Min Act: -0.1700

Data Index: 2624232 (Open Web Text)

Max Activating Token Index: 171

Text #11

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3288. Min Act: -0.1700

Data Index: 418330 (Open Web Text)

Max Activating Token Index: 1010

Text #12

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3233. Min Act: -0.1700

Data Index: 184264 (Open Web Text)

Max Activating Token Index: 252

Text #13

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3267. Min Act: -0.1700

Data Index: 4650450 (Open Web Text)

Max Activating Token Index: 145

Text #14

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3313. Min Act: -0.1700

Data Index: 2033887 (Open Web Text)

Max Activating Token Index: 756

Text #15

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3251. Min Act: -0.1700

Data Index: 2957987 (Open Web Text)

Max Activating Token Index: 761

Text #16

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3143. Min Act: -0.1700

Data Index: 4107279 (Open Web Text)

Max Activating Token Index: 444

Text #17

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3125. Min Act: -0.1700

Data Index: 2938629 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3108. Min Act: -0.1700

Data Index: 8102924 (Open Web Text)

Max Activating Token Index: 629

Text #19

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3129. Min Act: -0.1700

Data Index: 843374 (Open Web Text)

Max Activating Token Index: 807