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

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

Neuron 200 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: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0002

Data Index: 15492 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0472. Min Act: -0.0002

Data Index: 330257 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0464. Min Act: -0.0002

Data Index: 157063 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0496. Min Act: -0.0002

Data Index: 627821 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0546. Min Act: -0.0002

Data Index: 988488 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0504. Min Act: -0.0002

Data Index: 241763 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0521. Min Act: -0.0002

Data Index: 586930 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0524. Min Act: -0.0002

Data Index: 260645 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1619444 (Python Code)

Max Activating Token Index: 701

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1308371 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1184450 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1184870 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0469. Min Act: -0.0002

Data Index: 8525 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1190650 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0449. Min Act: -0.0002

Data Index: 448284 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0450. Min Act: -0.0002

Data Index: 867765 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0449. Min Act: -0.0002

Data Index: 206190 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0441. Min Act: -0.0002

Data Index: 745263 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1033450 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0425. Min Act: -0.0002

Data Index: 660271 (C4 (Web Text))

Max Activating Token Index: 164