Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5936 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1517762 (Python Code)

Max Activating Token Index: 348

Text #1

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1650. Min Act: -0.0000

Data Index: 412724 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1567. Min Act: -0.0000

Data Index: 144338 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1447. Min Act: -0.0000

Data Index: 199873 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1193834 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1433278 (Python Code)

Max Activating Token Index: 467

Text #6

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1023176 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1279. Min Act: -0.0000

Data Index: 252229 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1008704 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1269. Min Act: -0.0000

Data Index: 245238 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1223009 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1221. Min Act: -0.0000

Data Index: 478424 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1307. Min Act: -0.0000

Data Index: 14309 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1184887 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1289. Min Act: -0.0000

Data Index: 879786 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1239. Min Act: -0.0000

Data Index: 337839 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1230. Min Act: -0.0000

Data Index: 104928 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1163. Min Act: -0.0000

Data Index: 733658 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1163. Min Act: -0.0000

Data Index: 433853 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1516173 (Python Code)

Max Activating Token Index: 520