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

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

Neuron 3206 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 131922 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1322886 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0169. Min Act: -0.0002

Data Index: 912390 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0165. Min Act: -0.0003

Data Index: 141958 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1185955 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0162. Min Act: -0.0003

Data Index: 267060 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1644297 (Python Code)

Max Activating Token Index: 854

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1525238 (Python Code)

Max Activating Token Index: 903

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1483397 (Python Code)

Max Activating Token Index: 512

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0156. Min Act: -0.0003

Data Index: 637525 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0152. Min Act: -0.0003

Data Index: 651669 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1510851 (Python Code)

Max Activating Token Index: 31

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0151. Min Act: -0.0003

Data Index: 645317 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1499122 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1370549 (Python Code)

Max Activating Token Index: 48

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0149. Min Act: -0.0003

Data Index: 316338 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1491636 (Python Code)

Max Activating Token Index: 309

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1227332 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1362589 (Python Code)

Max Activating Token Index: 87

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1469636 (Python Code)

Max Activating Token Index: 557