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

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

Neuron 5108 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 29003 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 1573435 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 1457438 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 26212 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 22323 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 4151 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 11886 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 28851 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 188 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 12118 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 12424 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 11423 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 24133 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 3179 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 27797 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 13370 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 19506 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 28808 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 21205 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0002

Data Index: 20067 (C4 (Web Text))

Max Activating Token Index: 1