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

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

Neuron 1167 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0003

Data Index: 479685 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0414. Min Act: -0.0002

Data Index: 749731 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0352. Min Act: -0.0002

Data Index: 554528 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1216620 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0364. Min Act: -0.0003

Data Index: 893745 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1176698 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1291292 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0287. Min Act: -0.0003

Data Index: 331325 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0368. Min Act: -0.0003

Data Index: 458888 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0327. Min Act: -0.0002

Data Index: 987340 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0319. Min Act: -0.0002

Data Index: 342969 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0298. Min Act: -0.0003

Data Index: 674585 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1335287 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0292. Min Act: -0.0003

Data Index: 8971 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0302. Min Act: -0.0003

Data Index: 938715 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0267. Min Act: -0.0003

Data Index: 697741 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0298. Min Act: -0.0002

Data Index: 502936 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0247. Min Act: -0.0003

Data Index: 406990 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0282. Min Act: -0.0003

Data Index: 368699 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0285. Min Act: -0.0002

Data Index: 180069 (C4 (Web Text))

Max Activating Token Index: 116