Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 84 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0006

Data Index: 937659 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0332. Min Act: -0.0006

Data Index: 1217836 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0318. Min Act: -0.0006

Data Index: 697745 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0324. Min Act: -0.0006

Data Index: 282207 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0312. Min Act: -0.0006

Data Index: 135683 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0324. Min Act: -0.0006

Data Index: 788749 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0314. Min Act: -0.0006

Data Index: 577921 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0309. Min Act: -0.0006

Data Index: 833857 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0314. Min Act: -0.0006

Data Index: 1097507 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0300. Min Act: -0.0006

Data Index: 753869 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1154579 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0303. Min Act: -0.0006

Data Index: 798969 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1327539 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1009610 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0299. Min Act: -0.0006

Data Index: 249577 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0285. Min Act: -0.0006

Data Index: 936859 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0304. Min Act: -0.0006

Data Index: 341268 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0298. Min Act: -0.0006

Data Index: 1209872 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0298. Min Act: -0.0006

Data Index: 251595 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1112627 (C4 (Web Text))

Max Activating Token Index: 554