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

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

Neuron 505 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: 0.0386. Min Range: -0.0386

Max Act: 0.0375. Min Act: -0.0001

Data Index: 204495 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1029200 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0384. Min Act: -0.0001

Data Index: 580604 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0386. Min Act: -0.0002

Data Index: 529168 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0375. Min Act: -0.0001

Data Index: 112932 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1237334 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1335815 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0361. Min Act: -0.0001

Data Index: 958016 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0374. Min Act: -0.0002

Data Index: 156955 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0368. Min Act: -0.0000

Data Index: 313578 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0364. Min Act: -0.0002

Data Index: 592792 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1289905 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0354. Min Act: -0.0001

Data Index: 571305 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0347. Min Act: -0.0002

Data Index: 769506 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0358. Min Act: -0.0001

Data Index: 1326115 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0344. Min Act: -0.0002

Data Index: 423117 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0347. Min Act: -0.0002

Data Index: 223099 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1247217 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1417623 (Python Code)

Max Activating Token Index: 323

Text #19

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0357. Min Act: -0.0001

Data Index: 610799 (C4 (Web Text))

Max Activating Token Index: 33