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

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

Neuron 1840 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: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1261475 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0440. Min Act: -0.0004

Data Index: 297156 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1130822 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0453. Min Act: -0.0004

Data Index: 346215 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0437. Min Act: -0.0003

Data Index: 185734 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0442. Min Act: -0.0003

Data Index: 651201 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1225552 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0417. Min Act: -0.0003

Data Index: 396734 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1141226 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0401. Min Act: -0.0003

Data Index: 748252 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0399. Min Act: -0.0003

Data Index: 825036 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1218061 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0401. Min Act: -0.0003

Data Index: 905802 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0407. Min Act: -0.0003

Data Index: 39689 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0404. Min Act: -0.0003

Data Index: 759350 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0398. Min Act: -0.0004

Data Index: 339885 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0385. Min Act: -0.0003

Data Index: 368391 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1005099 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0386. Min Act: -0.0003

Data Index: 100720 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0363. Min Act: -0.0003

Data Index: 791572 (C4 (Web Text))

Max Activating Token Index: 840