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

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

Neuron 4536 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: 0.0176. Min Range: -0.0176

Max Act: 0.0174. Min Act: -0.0002

Data Index: 287664 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0174. Min Act: -0.0002

Data Index: 136295 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0174. Min Act: -0.0002

Data Index: 496931 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1241085 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0174. Min Act: -0.0002

Data Index: 475214 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0174. Min Act: -0.0002

Data Index: 569336 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1276907 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1303576 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1184031 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0168. Min Act: -0.0002

Data Index: 304290 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0165. Min Act: -0.0002

Data Index: 883472 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0166. Min Act: -0.0002

Data Index: 531912 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0159. Min Act: -0.0002

Data Index: 700286 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0162. Min Act: -0.0002

Data Index: 799529 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0162. Min Act: -0.0002

Data Index: 539720 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0161. Min Act: -0.0002

Data Index: 557716 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0161. Min Act: -0.0002

Data Index: 472213 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0160. Min Act: -0.0002

Data Index: 875585 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0160. Min Act: -0.0002

Data Index: 482924 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0159. Min Act: -0.0002

Data Index: 500225 (C4 (Web Text))

Max Activating Token Index: 954