Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 5 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0388. Min Act: -0.0006

Data Index: 394910 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0006

Data Index: 316623 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0363. Min Act: -0.0006

Data Index: 774908 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0371. Min Act: -0.0006

Data Index: 1099506 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0342. Min Act: -0.0006

Data Index: 520872 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0334. Min Act: -0.0006

Data Index: 515125 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0319. Min Act: -0.0006

Data Index: 1028544 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0339. Min Act: -0.0006

Data Index: 586686 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0329. Min Act: -0.0006

Data Index: 495306 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0326. Min Act: -0.0006

Data Index: 168444 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0310. Min Act: -0.0006

Data Index: 746755 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0318. Min Act: -0.0006

Data Index: 131917 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0337. Min Act: -0.0006

Data Index: 856143 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0336. Min Act: -0.0006

Data Index: 422498 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0336. Min Act: -0.0005

Data Index: 676555 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0320. Min Act: -0.0006

Data Index: 361026 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0332. Min Act: -0.0006

Data Index: 946093 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0322. Min Act: -0.0006

Data Index: 643819 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0314. Min Act: -0.0006

Data Index: 378439 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0306. Min Act: -0.0006

Data Index: 523625 (C4 (Web Text))

Max Activating Token Index: 467