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

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

Neuron 1658 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: 0.0404. Min Range: -0.0404

Max Act: 0.0392. Min Act: -0.0003

Data Index: 98574 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0003

Data Index: 231409 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0363. Min Act: -0.0002

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0336. Min Act: -0.0002

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1153153 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1336589 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0300. Min Act: -0.0003

Data Index: 994708 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0317. Min Act: -0.0002

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0318. Min Act: -0.0003

Data Index: 583131 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1636710 (Python Code)

Max Activating Token Index: 596

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0286. Min Act: -0.0003

Data Index: 860052 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1266074 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1435150 (Python Code)

Max Activating Token Index: 55

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0271. Min Act: -0.0003

Data Index: 347435 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1036112 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0269. Min Act: -0.0003

Data Index: 169722 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0265. Min Act: -0.0003

Data Index: 18175 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0231. Min Act: -0.0003

Data Index: 449771 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1629522 (Python Code)

Max Activating Token Index: 65