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

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

Neuron 4593 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0451. Min Act: -0.0000

Data Index: 382939 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0000

Data Index: 839851 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0451. Min Act: -0.0000

Data Index: 806189 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0417. Min Act: -0.0000

Data Index: 434409 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0428. Min Act: -0.0000

Data Index: 308043 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0422. Min Act: -0.0000

Data Index: 1112698 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0399. Min Act: -0.0000

Data Index: 658830 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0394. Min Act: -0.0000

Data Index: 1527512 (Python Code)

Max Activating Token Index: 721

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0414. Min Act: -0.0000

Data Index: 649647 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0411. Min Act: -0.0000

Data Index: 1164598 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0379. Min Act: -0.0000

Data Index: 338914 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0391. Min Act: -0.0000

Data Index: 565009 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0387. Min Act: -0.0000

Data Index: 868994 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0370. Min Act: -0.0000

Data Index: 104548 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0394. Min Act: -0.0000

Data Index: 86309 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1319334 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0370. Min Act: -0.0000

Data Index: 75916 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0323. Min Act: -0.0000

Data Index: 281781 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0366. Min Act: -0.0000

Data Index: 898735 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0336. Min Act: -0.0000

Data Index: 468906 (C4 (Web Text))

Max Activating Token Index: 658