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

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

Neuron 4126 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.8036. Min Act: -0.0000

Data Index: 498008 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.7392. Min Act: -0.0000

Data Index: 152479 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.4401. Min Act: -0.0000

Data Index: 374250 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.2227. Min Act: -0.0000

Data Index: 196180 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.0861. Min Act: -0.0000

Data Index: 446506 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.9105. Min Act: -0.0000

Data Index: 38444 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.6644. Min Act: -0.0000

Data Index: 459633 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.9513. Min Act: -0.0000

Data Index: 1229822 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.8983. Min Act: -0.0000

Data Index: 272969 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.8617. Min Act: -0.0000

Data Index: 518900 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.0122. Min Act: -0.0000

Data Index: 456749 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.7639. Min Act: -0.0000

Data Index: 396266 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.8735. Min Act: -0.0000

Data Index: 602724 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.6943. Min Act: -0.0000

Data Index: 650886 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.5103. Min Act: -0.0000

Data Index: 1150683 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.6747. Min Act: -0.0000

Data Index: 901975 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.6602. Min Act: -0.0000

Data Index: 228485 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.3498. Min Act: -0.0000

Data Index: 555091 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.3026. Min Act: -0.0000

Data Index: 1110421 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.4917. Min Act: -0.0000

Data Index: 748628 (C4 (Web Text))

Max Activating Token Index: 926