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

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

Neuron 3416 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0283. Min Range: -1.0283

Max Act: 1.0283. Min Act: -0.0000

Data Index: 220306 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9720. Min Act: -0.0000

Data Index: 484067 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9871. Min Act: -0.0000

Data Index: 856580 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9456. Min Act: -0.0000

Data Index: 16061 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9380. Min Act: -0.0000

Data Index: 206168 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9387. Min Act: -0.0000

Data Index: 120312 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9301. Min Act: -0.0000

Data Index: 437764 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1283168 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9132. Min Act: -0.0000

Data Index: 742482 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9194. Min Act: -0.0000

Data Index: 734752 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9349. Min Act: -0.0000

Data Index: 121277 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9293. Min Act: -0.0000

Data Index: 20078 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9501. Min Act: -0.0001

Data Index: 192414 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1261204 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8659. Min Act: -0.0000

Data Index: 765483 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7890. Min Act: -0.0000

Data Index: 14838 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1138369 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8319. Min Act: -0.0000

Data Index: 53808 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8469. Min Act: -0.0000

Data Index: 792680 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8173. Min Act: -0.0000

Data Index: 355865 (C4 (Web Text))

Max Activating Token Index: 940