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

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

Neuron 4959 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1500111 (Python Code)

Max Activating Token Index: 582

Text #1

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1576299 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1525302 (Python Code)

Max Activating Token Index: 331

Text #3

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1549170 (Python Code)

Max Activating Token Index: 158

Text #4

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1512620 (Python Code)

Max Activating Token Index: 556

Text #5

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1553072 (Python Code)

Max Activating Token Index: 74

Text #6

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1486183 (Python Code)

Max Activating Token Index: 749

Text #7

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1505547 (Python Code)

Max Activating Token Index: 306

Text #8

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0148. Min Act: -0.0002

Data Index: 448055 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0146. Min Act: -0.0002

Data Index: 148199 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1561641 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1619130 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1608824 (Python Code)

Max Activating Token Index: 467

Text #13

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1622447 (Python Code)

Max Activating Token Index: 354

Text #14

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1486371 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1611705 (Python Code)

Max Activating Token Index: 648

Text #16

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1329567 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1560624 (Python Code)

Max Activating Token Index: 461

Text #18

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1587066 (Python Code)

Max Activating Token Index: 113

Text #19

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1248990 (C4 (Web Text))

Max Activating Token Index: 73