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

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

Neuron 1163 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: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0002

Data Index: 982948 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1157614 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0417. Min Act: -0.0002

Data Index: 193476 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0465. Min Act: -0.0002

Data Index: 278697 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0393. Min Act: -0.0002

Data Index: 767659 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0386. Min Act: -0.0002

Data Index: 109838 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0411. Min Act: -0.0002

Data Index: 427847 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0446. Min Act: -0.0002

Data Index: 760648 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1278475 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0387. Min Act: -0.0002

Data Index: 513111 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0392. Min Act: -0.0002

Data Index: 603523 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0376. Min Act: -0.0002

Data Index: 849968 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1075103 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0382. Min Act: -0.0002

Data Index: 661191 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0411. Min Act: -0.0002

Data Index: 159292 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0395. Min Act: -0.0002

Data Index: 611379 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1096060 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1266898 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1019515 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0366. Min Act: -0.0002

Data Index: 575194 (C4 (Web Text))

Max Activating Token Index: 997