Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5738 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1344879 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0469. Min Act: -0.0002

Data Index: 388705 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0499. Min Act: -0.0002

Data Index: 393694 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1044440 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0474. Min Act: -0.0002

Data Index: 351749 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0451. Min Act: -0.0002

Data Index: 863058 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0444. Min Act: -0.0002

Data Index: 539869 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0447. Min Act: -0.0002

Data Index: 719098 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0414. Min Act: -0.0002

Data Index: 927042 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0417. Min Act: -0.0002

Data Index: 743779 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0407. Min Act: -0.0002

Data Index: 843502 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0414. Min Act: -0.0002

Data Index: 106957 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0420. Min Act: -0.0002

Data Index: 345090 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0402. Min Act: -0.0002

Data Index: 36922 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0413. Min Act: -0.0002

Data Index: 163777 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0380. Min Act: -0.0002

Data Index: 548238 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1156253 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0362. Min Act: -0.0002

Data Index: 257334 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1326396 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0354. Min Act: -0.0002

Data Index: 779219 (C4 (Web Text))

Max Activating Token Index: 787