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

Dataset: Open Web Text

Neuron 1003 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: 1.3893. Min Range: -1.3893

Max Act: 1.3893. Min Act: -0.1700

Data Index: 8759522 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3670. Min Act: -0.1700

Data Index: 7007857 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3567. Min Act: -0.1700

Data Index: 6244044 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3683. Min Act: -0.1700

Data Index: 914892 (Open Web Text)

Max Activating Token Index: 106

Text #4

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3557. Min Act: -0.1700

Data Index: 3440574 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3574. Min Act: -0.1700

Data Index: 318548 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3512. Min Act: -0.1700

Data Index: 1529790 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3426. Min Act: -0.1700

Data Index: 2020675 (Open Web Text)

Max Activating Token Index: 33

Text #8

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3356. Min Act: -0.1700

Data Index: 7695328 (Open Web Text)

Max Activating Token Index: 370

Text #9

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3213. Min Act: -0.1700

Data Index: 3913709 (Open Web Text)

Max Activating Token Index: 513

Text #10

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3296. Min Act: -0.1700

Data Index: 2856114 (Open Web Text)

Max Activating Token Index: 55

Text #11

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3233. Min Act: -0.1700

Data Index: 3969594 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3341. Min Act: -0.1700

Data Index: 2608893 (Open Web Text)

Max Activating Token Index: 27

Text #13

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3222. Min Act: -0.1700

Data Index: 3266545 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3324. Min Act: -0.1700

Data Index: 2489288 (Open Web Text)

Max Activating Token Index: 174

Text #15

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3180. Min Act: -0.1700

Data Index: 4870144 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3230. Min Act: -0.1700

Data Index: 288494 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3189. Min Act: -0.1700

Data Index: 5541628 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3180. Min Act: -0.1700

Data Index: 1645 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3214. Min Act: -0.1700

Data Index: 7242724 (Open Web Text)

Max Activating Token Index: 51