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

Dataset: Open Web Text

Neuron 1681 in Layer 2

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: 0.3919. Min Range: -0.3919

Max Act: 0.3919. Min Act: -0.1700

Data Index: 3486591 (Open Web Text)

Max Activating Token Index: 97

Text #1

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3750. Min Act: -0.1700

Data Index: 7876453 (Open Web Text)

Max Activating Token Index: 943

Text #2

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3710. Min Act: -0.1700

Data Index: 2332003 (Open Web Text)

Max Activating Token Index: 970

Text #3

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3641. Min Act: -0.1700

Data Index: 8573759 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3620. Min Act: -0.1700

Data Index: 1845752 (Open Web Text)

Max Activating Token Index: 302

Text #5

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3696. Min Act: -0.1700

Data Index: 3444131 (Open Web Text)

Max Activating Token Index: 143

Text #6

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3516. Min Act: -0.1700

Data Index: 3052393 (Open Web Text)

Max Activating Token Index: 338

Text #7

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3465. Min Act: -0.1700

Data Index: 5534558 (Open Web Text)

Max Activating Token Index: 885

Text #8

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3487. Min Act: -0.1700

Data Index: 1002004 (Open Web Text)

Max Activating Token Index: 246

Text #9

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3305. Min Act: -0.1700

Data Index: 4879945 (Open Web Text)

Max Activating Token Index: 684

Text #10

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3312. Min Act: -0.1700

Data Index: 6494085 (Open Web Text)

Max Activating Token Index: 115

Text #11

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3323. Min Act: -0.1700

Data Index: 9632 (Open Web Text)

Max Activating Token Index: 79

Text #12

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3278. Min Act: -0.1700

Data Index: 2795767 (Open Web Text)

Max Activating Token Index: 94

Text #13

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3324. Min Act: -0.1700

Data Index: 7042078 (Open Web Text)

Max Activating Token Index: 336

Text #14

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3347. Min Act: -0.1700

Data Index: 7110686 (Open Web Text)

Max Activating Token Index: 923

Text #15

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3238. Min Act: -0.1700

Data Index: 3635268 (Open Web Text)

Max Activating Token Index: 784

Text #16

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3224. Min Act: -0.1700

Data Index: 6519606 (Open Web Text)

Max Activating Token Index: 382

Text #17

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3229. Min Act: -0.1700

Data Index: 2593031 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3183. Min Act: -0.1700

Data Index: 434042 (Open Web Text)

Max Activating Token Index: 598

Text #19

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3218. Min Act: -0.1700

Data Index: 4968779 (Open Web Text)

Max Activating Token Index: 794