Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1255 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1359. Min Act: -0.0001

Data Index: 251856 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1286. Min Act: -0.0001

Data Index: 152327 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1266. Min Act: -0.0001

Data Index: 48405 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1155. Min Act: -0.0001

Data Index: 270799 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1189. Min Act: -0.0000

Data Index: 24921 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1180. Min Act: -0.0001

Data Index: 239630 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1247. Min Act: -0.0000

Data Index: 44421 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1162. Min Act: -0.0000

Data Index: 218811 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1152. Min Act: -0.0000

Data Index: 567361 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1237. Min Act: -0.0000

Data Index: 871693 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1196. Min Act: -0.0001

Data Index: 31067 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1136. Min Act: -0.0000

Data Index: 860377 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1077. Min Act: -0.0001

Data Index: 996986 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1101. Min Act: -0.0000

Data Index: 563311 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1259572 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1107. Min Act: -0.0001

Data Index: 207507 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1075. Min Act: -0.0001

Data Index: 868211 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1053. Min Act: -0.0000

Data Index: 773289 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1094. Min Act: -0.0000

Data Index: 409866 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1055. Min Act: -0.0001

Data Index: 875817 (C4 (Web Text))

Max Activating Token Index: 85