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

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

Neuron 2421 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: 0.0403. Min Range: -0.0403

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1358947 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0275. Min Act: -0.0003

Data Index: 111800 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0265. Min Act: -0.0003

Data Index: 316383 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0225. Min Act: -0.0003

Data Index: 499165 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0228. Min Act: -0.0003

Data Index: 241721 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1099185 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0205. Min Act: -0.0003

Data Index: 888521 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0193. Min Act: -0.0003

Data Index: 695472 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0188. Min Act: -0.0003

Data Index: 114765 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1220776 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0190. Min Act: -0.0003

Data Index: 740246 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1054346 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0187. Min Act: -0.0002

Data Index: 172327 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1141284 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0182. Min Act: -0.0003

Data Index: 689034 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0178. Min Act: -0.0003

Data Index: 687121 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0170. Min Act: -0.0003

Data Index: 956644 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0173. Min Act: -0.0003

Data Index: 157321 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0167. Min Act: -0.0002

Data Index: 822627 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0171. Min Act: -0.0003

Data Index: 149469 (C4 (Web Text))

Max Activating Token Index: 745