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

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

Neuron 3508 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0003

Data Index: 743183 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0432. Min Act: -0.0003

Data Index: 689731 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0416. Min Act: -0.0003

Data Index: 671965 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0407. Min Act: -0.0003

Data Index: 694400 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0388. Min Act: -0.0003

Data Index: 372005 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0392. Min Act: -0.0003

Data Index: 944994 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0380. Min Act: -0.0003

Data Index: 312343 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0345. Min Act: -0.0003

Data Index: 619783 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0359. Min Act: -0.0003

Data Index: 956320 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0352. Min Act: -0.0003

Data Index: 415319 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0362. Min Act: -0.0003

Data Index: 648914 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0351. Min Act: -0.0002

Data Index: 810447 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0364. Min Act: -0.0003

Data Index: 625147 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0378. Min Act: -0.0003

Data Index: 694554 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0362. Min Act: -0.0003

Data Index: 96819 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0345. Min Act: -0.0003

Data Index: 656504 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0358. Min Act: -0.0003

Data Index: 640431 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1432025 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1282238 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0349. Min Act: -0.0003

Data Index: 375214 (C4 (Web Text))

Max Activating Token Index: 345