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

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

Neuron 1660 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0395. Min Act: -0.0003

Data Index: 479189 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0395. Min Act: -0.0002

Data Index: 603145 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0003

Data Index: 1402757 (Python Code)

Max Activating Token Index: 965

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1217022 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0356. Min Act: -0.0002

Data Index: 897413 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0359. Min Act: -0.0004

Data Index: 1566255 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0345. Min Act: -0.0003

Data Index: 286789 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1650646 (Python Code)

Max Activating Token Index: 305

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0345. Min Act: -0.0003

Data Index: 940199 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0337. Min Act: -0.0002

Data Index: 765009 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1318512 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0315. Min Act: -0.0003

Data Index: 337062 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0325. Min Act: -0.0003

Data Index: 997898 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1285843 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1193489 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0315. Min Act: -0.0003

Data Index: 984015 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0324. Min Act: -0.0003

Data Index: 147850 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0314. Min Act: -0.0003

Data Index: 712796 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1089596 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0317. Min Act: -0.0001

Data Index: 458571 (C4 (Web Text))

Max Activating Token Index: 1005