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

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

Neuron 3625 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0221. Min Act: -0.0002

Data Index: 410905 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1287019 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0186. Min Act: -0.0002

Data Index: 756856 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1240 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1529059 (Python Code)

Max Activating Token Index: 336

Text #5

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1650499 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1638870 (Python Code)

Max Activating Token Index: 473

Text #7

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0167. Min Act: -0.0003

Data Index: 971322 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0168. Min Act: -0.0003

Data Index: 244374 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0166. Min Act: -0.0002

Data Index: 143746 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1569083 (Python Code)

Max Activating Token Index: 1008

Text #11

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1440383 (Python Code)

Max Activating Token Index: 458

Text #12

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1340658 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0156. Min Act: -0.0003

Data Index: 735060 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0161. Min Act: -0.0002

Data Index: 113279 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0161. Min Act: -0.0002

Data Index: 371565 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1515272 (Python Code)

Max Activating Token Index: 956

Text #17

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0161. Min Act: -0.0003

Data Index: 7844 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1562954 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1395028 (Python Code)

Max Activating Token Index: 608