Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 680 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.5949. Min Act: -0.0001

Data Index: 128232 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.5068. Min Act: -0.0000

Data Index: 499550 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.4706. Min Act: -0.0000

Data Index: 380288 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1265566 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.4508. Min Act: -0.0000

Data Index: 75429 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.4280. Min Act: -0.0000

Data Index: 834123 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.4144. Min Act: 0.0000

Data Index: 165946 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3977. Min Act: -0.0000

Data Index: 771624 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3966. Min Act: -0.0000

Data Index: 583488 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3886. Min Act: -0.0000

Data Index: 52759 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3791. Min Act: -0.0001

Data Index: 356068 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3857. Min Act: -0.0000

Data Index: 521439 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3664. Min Act: 0.0000

Data Index: 1021140 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3595. Min Act: 0.0000

Data Index: 1027338 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3512. Min Act: -0.0001

Data Index: 37119 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3417. Min Act: -0.0000

Data Index: 41672 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3435. Min Act: -0.0001

Data Index: 388662 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3393. Min Act: -0.0001

Data Index: 722154 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3252. Min Act: 0.0000

Data Index: 778966 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.5949. Min Range: -0.5949

Max Act: 0.3373. Min Act: 0.0000

Data Index: 127070 (C4 (Web Text))

Max Activating Token Index: 121