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

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

Neuron 3529 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4978. Min Act: -0.0000

Data Index: 202514 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1292324 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3680. Min Act: -0.0000

Data Index: 197686 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1548525 (Python Code)

Max Activating Token Index: 398

Text #4

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1377367 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2958. Min Act: -0.0000

Data Index: 806232 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3024. Min Act: -0.0000

Data Index: 749096 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2746. Min Act: -0.0000

Data Index: 642946 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2723. Min Act: -0.0000

Data Index: 952145 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2887. Min Act: -0.0000

Data Index: 346963 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2790. Min Act: -0.0000

Data Index: 926976 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2630. Min Act: -0.0000

Data Index: 193467 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2808. Min Act: -0.0000

Data Index: 260704 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2386. Min Act: -0.0000

Data Index: 672896 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1282087 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2556. Min Act: -0.0000

Data Index: 687501 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1153260 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2530. Min Act: -0.0000

Data Index: 484537 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2438. Min Act: -0.0000

Data Index: 328484 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1065319 (C4 (Web Text))

Max Activating Token Index: 394