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

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

Neuron 827 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: 0.0255. Min Range: -0.0255

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1269390 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1233941 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0192. Min Act: -0.0003

Data Index: 89205 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1440522 (Python Code)

Max Activating Token Index: 368

Text #4

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0193. Min Act: -0.0003

Data Index: 240447 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1179130 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1178937 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0170. Min Act: -0.0003

Data Index: 122256 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0171. Min Act: -0.0003

Data Index: 837276 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1016590 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0172. Min Act: -0.0003

Data Index: 90099 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1254580 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1435639 (Python Code)

Max Activating Token Index: 135

Text #13

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1238220 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1122126 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1545748 (Python Code)

Max Activating Token Index: 475

Text #16

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1365751 (Python Code)

Max Activating Token Index: 487

Text #17

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1521471 (Python Code)

Max Activating Token Index: 941

Text #18

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0163. Min Act: -0.0003

Data Index: 621650 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0162. Min Act: -0.0002

Data Index: 924233 (C4 (Web Text))

Max Activating Token Index: 914