Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 976 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1195839 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0501. Min Act: -0.0003

Data Index: 116715 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1473264 (Python Code)

Max Activating Token Index: 1008

Text #3

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0420. Min Act: -0.0003

Data Index: 146682 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0422. Min Act: -0.0003

Data Index: 196696 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0397. Min Act: -0.0003

Data Index: 315823 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1240791 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0421. Min Act: -0.0003

Data Index: 752736 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0391. Min Act: -0.0003

Data Index: 922478 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0366. Min Act: -0.0003

Data Index: 138377 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0366. Min Act: -0.0004

Data Index: 579040 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1196718 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0377. Min Act: -0.0002

Data Index: 487690 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1424036 (Python Code)

Max Activating Token Index: 702

Text #14

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0373. Min Act: -0.0003

Data Index: 633017 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0374. Min Act: -0.0003

Data Index: 698433 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0372. Min Act: -0.0003

Data Index: 284225 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1195222 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1321196 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0363. Min Act: -0.0002

Data Index: 394583 (C4 (Web Text))

Max Activating Token Index: 525