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

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

Neuron 4971 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: 0.0656. Min Range: -0.0656

Max Act: 0.0656. Min Act: -0.0002

Data Index: 763562 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0590. Min Act: -0.0002

Data Index: 381463 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0512. Min Act: -0.0003

Data Index: 408220 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1283389 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1292708 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0451. Min Act: -0.0003

Data Index: 660588 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1099555 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0427. Min Act: -0.0003

Data Index: 91446 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0417. Min Act: -0.0003

Data Index: 166144 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0400. Min Act: -0.0003

Data Index: 397711 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0397. Min Act: -0.0003

Data Index: 155340 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0415. Min Act: -0.0002

Data Index: 912399 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1295703 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1104326 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0396. Min Act: -0.0003

Data Index: 948207 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0387. Min Act: -0.0002

Data Index: 177100 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0385. Min Act: -0.0003

Data Index: 332387 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0374. Min Act: -0.0003

Data Index: 197585 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0379. Min Act: -0.0002

Data Index: 814192 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1096643 (C4 (Web Text))

Max Activating Token Index: 202