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

Dataset: Open Web Text

Neuron 1920 in Layer 5

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: 3.3048. Min Range: -3.3048

Max Act: 3.3048. Min Act: -0.1700

Data Index: 4107282 (Open Web Text)

Max Activating Token Index: 327

Text #1

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2601. Min Act: -0.1700

Data Index: 8619873 (Open Web Text)

Max Activating Token Index: 725

Text #2

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2350. Min Act: -0.1700

Data Index: 2666620 (Open Web Text)

Max Activating Token Index: 250

Text #3

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2488. Min Act: -0.1700

Data Index: 89857 (Open Web Text)

Max Activating Token Index: 443

Text #4

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2238. Min Act: -0.1700

Data Index: 3840989 (Open Web Text)

Max Activating Token Index: 147

Text #5

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2428. Min Act: -0.1700

Data Index: 5912401 (Open Web Text)

Max Activating Token Index: 690

Text #6

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2160. Min Act: -0.1700

Data Index: 296401 (Open Web Text)

Max Activating Token Index: 641

Text #7

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2162. Min Act: -0.1700

Data Index: 2028004 (Open Web Text)

Max Activating Token Index: 339

Text #8

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2215. Min Act: -0.1700

Data Index: 672294 (Open Web Text)

Max Activating Token Index: 163

Text #9

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.1926. Min Act: -0.1700

Data Index: 8098424 (Open Web Text)

Max Activating Token Index: 629

Text #10

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2394. Min Act: -0.1700

Data Index: 1894591 (Open Web Text)

Max Activating Token Index: 726

Text #11

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2241. Min Act: -0.1700

Data Index: 1812385 (Open Web Text)

Max Activating Token Index: 695

Text #12

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.1993. Min Act: -0.1700

Data Index: 1100504 (Open Web Text)

Max Activating Token Index: 112

Text #13

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2316. Min Act: -0.1700

Data Index: 1312985 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.1975. Min Act: -0.1700

Data Index: 8551145 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.1718. Min Act: -0.1700

Data Index: 2210727 (Open Web Text)

Max Activating Token Index: 946

Text #16

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.2031. Min Act: -0.1700

Data Index: 5117755 (Open Web Text)

Max Activating Token Index: 799

Text #17

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.1669. Min Act: -0.1700

Data Index: 5858037 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.1196. Min Act: -0.1700

Data Index: 3824109 (Open Web Text)

Max Activating Token Index: 507

Text #19

Max Range: 3.3048. Min Range: -3.3048

Max Act: 3.1205. Min Act: -0.1700

Data Index: 4257755 (Open Web Text)

Max Activating Token Index: 975