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

Dataset: Open Web Text

Neuron 1842 in Layer 0

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: 3.5278. Min Range: -3.5278

Max Act: 3.5278. Min Act: -0.1700

Data Index: 944680 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.4325. Min Act: -0.1700

Data Index: 5997867 (Open Web Text)

Max Activating Token Index: 30

Text #2

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.4203. Min Act: -0.1700

Data Index: 5685265 (Open Web Text)

Max Activating Token Index: 408

Text #3

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3727. Min Act: -0.1700

Data Index: 6317920 (Open Web Text)

Max Activating Token Index: 794

Text #4

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3857. Min Act: -0.1700

Data Index: 5928327 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3831. Min Act: -0.1700

Data Index: 2236133 (Open Web Text)

Max Activating Token Index: 791

Text #6

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3748. Min Act: -0.1700

Data Index: 156503 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3407. Min Act: -0.1700

Data Index: 5685266 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3501. Min Act: -0.1700

Data Index: 5352612 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3660. Min Act: -0.1700

Data Index: 1094403 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3363. Min Act: -0.1700

Data Index: 6164812 (Open Web Text)

Max Activating Token Index: 395

Text #11

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3106. Min Act: -0.1700

Data Index: 5500863 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3111. Min Act: -0.1700

Data Index: 1369224 (Open Web Text)

Max Activating Token Index: 714

Text #13

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3308. Min Act: -0.1700

Data Index: 7260351 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3179. Min Act: -0.1700

Data Index: 7141401 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3039. Min Act: -0.1700

Data Index: 5424437 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3106. Min Act: -0.1700

Data Index: 5837138 (Open Web Text)

Max Activating Token Index: 840

Text #17

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2927. Min Act: -0.1700

Data Index: 1269256 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2965. Min Act: -0.1700

Data Index: 2398946 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2996. Min Act: -0.1700

Data Index: 971991 (Open Web Text)

Max Activating Token Index: 6