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

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

Neuron 745 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: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0002

Data Index: 139107 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0406. Min Act: -0.0003

Data Index: 636993 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0403. Min Act: -0.0002

Data Index: 283632 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0398. Min Act: -0.0003

Data Index: 852881 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0363. Min Act: -0.0003

Data Index: 595840 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0358. Min Act: -0.0003

Data Index: 823157 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0336. Min Act: -0.0002

Data Index: 628219 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0331. Min Act: -0.0003

Data Index: 788436 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0323. Min Act: -0.0002

Data Index: 190878 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0316. Min Act: -0.0003

Data Index: 267295 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0315. Min Act: -0.0003

Data Index: 819201 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0312. Min Act: -0.0002

Data Index: 158345 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0309. Min Act: -0.0003

Data Index: 58722 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0306. Min Act: -0.0002

Data Index: 326968 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1354826 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0301. Min Act: -0.0002

Data Index: 309626 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1063854 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0303. Min Act: -0.0003

Data Index: 640836 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1166310 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0292. Min Act: -0.0002

Data Index: 260942 (C4 (Web Text))

Max Activating Token Index: 318