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

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

Neuron 4923 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: 0.0430. Min Range: -0.0430

Max Act: 0.0425. Min Act: -0.0002

Data Index: 461116 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0430. Min Act: -0.0002

Data Index: 704762 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0425. Min Act: -0.0002

Data Index: 459795 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1333799 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0384. Min Act: -0.0002

Data Index: 449342 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0419. Min Act: -0.0002

Data Index: 537766 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0426. Min Act: -0.0002

Data Index: 522090 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1054429 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0392. Min Act: -0.0002

Data Index: 358345 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0386. Min Act: -0.0002

Data Index: 452688 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0374. Min Act: -0.0002

Data Index: 645750 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1247527 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0348. Min Act: -0.0002

Data Index: 561683 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0370. Min Act: -0.0002

Data Index: 449638 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0314. Min Act: -0.0002

Data Index: 752119 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0370. Min Act: -0.0002

Data Index: 223253 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0367. Min Act: -0.0002

Data Index: 791316 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0357. Min Act: -0.0002

Data Index: 778422 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0349. Min Act: -0.0002

Data Index: 762554 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0352. Min Act: -0.0002

Data Index: 920517 (C4 (Web Text))

Max Activating Token Index: 429