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

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

Neuron 1226 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: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 570196 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0159. Min Act: -0.0002

Data Index: 226097 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0160. Min Act: -0.0002

Data Index: 913992 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0156. Min Act: -0.0002

Data Index: 280280 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0154. Min Act: -0.0002

Data Index: 470585 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1044831 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0150. Min Act: -0.0002

Data Index: 425554 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1224955 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1016159 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0002

Data Index: 541024 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0146. Min Act: -0.0002

Data Index: 106833 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0146. Min Act: -0.0002

Data Index: 18845 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0145. Min Act: -0.0002

Data Index: 226964 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1303972 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0145. Min Act: -0.0002

Data Index: 956604 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0148. Min Act: -0.0002

Data Index: 453 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1092860 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0145. Min Act: -0.0002

Data Index: 949720 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0002

Data Index: 843823 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1328246 (C4 (Web Text))

Max Activating Token Index: 578