Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3638 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 57774 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0344. Min Act: -0.0002

Data Index: 187279 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0291. Min Act: -0.0002

Data Index: 600462 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0287. Min Act: -0.0002

Data Index: 198305 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0283. Min Act: -0.0002

Data Index: 967337 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0269. Min Act: -0.0002

Data Index: 100069 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1208600 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0250. Min Act: -0.0002

Data Index: 926783 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1401416 (Python Code)

Max Activating Token Index: 40

Text #9

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1073168 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0246. Min Act: -0.0002

Data Index: 671334 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0241. Min Act: -0.0002

Data Index: 572493 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0240. Min Act: -0.0002

Data Index: 382802 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1014698 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1154140 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0246. Min Act: -0.0002

Data Index: 673405 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0236. Min Act: -0.0002

Data Index: 515868 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0226. Min Act: -0.0002

Data Index: 819993 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1058969 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1023865 (C4 (Web Text))

Max Activating Token Index: 66