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

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

Neuron 990 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0521. Min Act: -0.0002

Data Index: 292085 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0446. Min Act: -0.0002

Data Index: 185670 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1361410 (Python Code)

Max Activating Token Index: 92

Text #3

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0411. Min Act: -0.0002

Data Index: 939014 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0390. Min Act: -0.0002

Data Index: 621117 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0376. Min Act: -0.0002

Data Index: 183321 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1171649 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1432860 (Python Code)

Max Activating Token Index: 539

Text #8

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0376. Min Act: -0.0002

Data Index: 742535 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0362. Min Act: -0.0002

Data Index: 545025 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1407666 (Python Code)

Max Activating Token Index: 387

Text #11

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0334. Min Act: -0.0002

Data Index: 78042 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0339. Min Act: -0.0002

Data Index: 246298 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1571361 (Python Code)

Max Activating Token Index: 379

Text #14

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0342. Min Act: -0.0002

Data Index: 78501 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0349. Min Act: -0.0002

Data Index: 278226 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0355. Min Act: -0.0002

Data Index: 482314 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1399714 (Python Code)

Max Activating Token Index: 994

Text #18

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0324. Min Act: -0.0002

Data Index: 269730 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1620253 (Python Code)

Max Activating Token Index: 520