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

Dataset: Open Web Text

Neuron 2234 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: 3.2362. Min Range: -3.2362

Max Act: 3.2362. Min Act: -0.1700

Data Index: 787543 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2253. Min Act: -0.1700

Data Index: 3723016 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2253. Min Act: -0.1700

Data Index: 8808346 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2253. Min Act: -0.1700

Data Index: 2108014 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2213. Min Act: -0.1700

Data Index: 3201346 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2123. Min Act: -0.1700

Data Index: 1962837 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2257. Min Act: -0.1700

Data Index: 6496200 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2178. Min Act: -0.1700

Data Index: 4669703 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2106. Min Act: -0.1700

Data Index: 998735 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2149. Min Act: -0.1700

Data Index: 8626994 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2056. Min Act: -0.1700

Data Index: 6125558 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2024. Min Act: -0.1700

Data Index: 2962049 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2015. Min Act: -0.1700

Data Index: 7222035 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.1859. Min Act: -0.1700

Data Index: 5302934 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.1912. Min Act: -0.1700

Data Index: 5704176 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.2000. Min Act: -0.1700

Data Index: 6847749 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.1857. Min Act: -0.1700

Data Index: 1040891 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.1948. Min Act: -0.1700

Data Index: 6615116 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.1944. Min Act: -0.1700

Data Index: 2509482 (Open Web Text)

Max Activating Token Index: 104

Text #19

Max Range: 3.2362. Min Range: -3.2362

Max Act: 3.1868. Min Act: -0.1700

Data Index: 5937437 (Open Web Text)

Max Activating Token Index: 6