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

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

Neuron 801 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: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0003

Data Index: 806891 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0167. Min Act: -0.0003

Data Index: 456530 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0162. Min Act: -0.0003

Data Index: 668565 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0161. Min Act: -0.0003

Data Index: 672376 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1158582 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0160. Min Act: -0.0003

Data Index: 267904 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1301774 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0157. Min Act: -0.0003

Data Index: 665027 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0003

Data Index: 336192 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0157. Min Act: -0.0003

Data Index: 336361 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1350581 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0003

Data Index: 373911 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0156. Min Act: -0.0003

Data Index: 850376 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0156. Min Act: -0.0003

Data Index: 1314821 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0156. Min Act: -0.0003

Data Index: 169391 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0003

Data Index: 896627 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0003

Data Index: 941533 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0152. Min Act: -0.0003

Data Index: 829471 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0003

Data Index: 236010 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1312544 (C4 (Web Text))

Max Activating Token Index: 591