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

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

Neuron 824 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: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1081573 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0407. Min Act: -0.0003

Data Index: 824462 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1345384 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0376. Min Act: -0.0003

Data Index: 332810 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0368. Min Act: -0.0003

Data Index: 352430 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1605274 (Python Code)

Max Activating Token Index: 716

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0356. Min Act: -0.0003

Data Index: 756831 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0343. Min Act: -0.0003

Data Index: 594081 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0353. Min Act: -0.0003

Data Index: 162072 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0349. Min Act: -0.0003

Data Index: 103470 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0365. Min Act: -0.0003

Data Index: 272554 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0359. Min Act: -0.0003

Data Index: 845252 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0355. Min Act: -0.0003

Data Index: 820371 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0342. Min Act: -0.0002

Data Index: 378948 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0341. Min Act: -0.0002

Data Index: 357641 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1065115 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0331. Min Act: -0.0003

Data Index: 982429 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0335. Min Act: -0.0003

Data Index: 932567 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0341. Min Act: -0.0004

Data Index: 697006 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0319. Min Act: -0.0002

Data Index: 217388 (C4 (Web Text))

Max Activating Token Index: 577