Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 410 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0176. Min Act: -0.0003

Data Index: 134249 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1238346 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1137099 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1278214 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1365180 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0157. Min Act: -0.0003

Data Index: 414861 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0150. Min Act: -0.0003

Data Index: 835764 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0137. Min Act: -0.0003

Data Index: 1529905 (Python Code)

Max Activating Token Index: 74

Text #8

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0140. Min Act: -0.0003

Data Index: 482663 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0139. Min Act: -0.0003

Data Index: 1285758 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0137. Min Act: -0.0003

Data Index: 1511497 (Python Code)

Max Activating Token Index: 409

Text #11

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1574522 (Python Code)

Max Activating Token Index: 227

Text #12

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1252367 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0134. Min Act: -0.0002

Data Index: 988458 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0133. Min Act: -0.0003

Data Index: 65607 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1025759 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1507069 (Python Code)

Max Activating Token Index: 243

Text #17

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0129. Min Act: -0.0003

Data Index: 186697 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1408789 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1364425 (Python Code)

Max Activating Token Index: 2