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

Dataset: Open Web Text

Neuron 2745 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: 3.9946. Min Range: -3.9946

Max Act: 3.9946. Min Act: -0.1700

Data Index: 2064667 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.9383. Min Act: -0.1700

Data Index: 6010835 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.9095. Min Act: -0.1700

Data Index: 7010796 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8110. Min Act: -0.1700

Data Index: 4724945 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8204. Min Act: -0.1700

Data Index: 7644492 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7983. Min Act: -0.1700

Data Index: 5156494 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8234. Min Act: -0.1700

Data Index: 1982119 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7435. Min Act: -0.1700

Data Index: 6566295 (Open Web Text)

Max Activating Token Index: 801

Text #8

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7677. Min Act: -0.1700

Data Index: 1681199 (Open Web Text)

Max Activating Token Index: 247

Text #9

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7399. Min Act: -0.1700

Data Index: 2382547 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7490. Min Act: -0.1700

Data Index: 5622921 (Open Web Text)

Max Activating Token Index: 805

Text #11

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7511. Min Act: -0.1700

Data Index: 7740188 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7334. Min Act: -0.1700

Data Index: 4791093 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7584. Min Act: -0.1700

Data Index: 4105203 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7593. Min Act: -0.1700

Data Index: 305381 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7136. Min Act: -0.1700

Data Index: 5704239 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7054. Min Act: -0.1700

Data Index: 1954812 (Open Web Text)

Max Activating Token Index: 918

Text #17

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7170. Min Act: -0.1700

Data Index: 141075 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7170. Min Act: -0.1700

Data Index: 989808 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7289. Min Act: -0.1700

Data Index: 5952597 (Open Web Text)

Max Activating Token Index: 2