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

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

Neuron 3916 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2160. Min Range: -1.2160

Max Act: 1.2160. Min Act: -0.0001

Data Index: 1142177 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.2160. Min Range: -1.2160

Max Act: 1.0154. Min Act: -0.0001

Data Index: 659707 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.8994. Min Act: -0.0001

Data Index: 979227 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.8902. Min Act: -0.0001

Data Index: 679651 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.9081. Min Act: -0.0001

Data Index: 999290 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.8183. Min Act: -0.0001

Data Index: 464686 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.8380. Min Act: -0.0001

Data Index: 1073488 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7997. Min Act: -0.0001

Data Index: 439538 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7870. Min Act: -0.0001

Data Index: 381296 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7928. Min Act: -0.0001

Data Index: 516594 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7219. Min Act: -0.0001

Data Index: 961931 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.8207. Min Act: -0.0001

Data Index: 1066490 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7887. Min Act: -0.0001

Data Index: 666661 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7988. Min Act: -0.0001

Data Index: 1357810 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7474. Min Act: -0.0001

Data Index: 110531 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7153. Min Act: -0.0001

Data Index: 327046 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7063. Min Act: -0.0001

Data Index: 854634 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7718. Min Act: -0.0001

Data Index: 1261859 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7004. Min Act: -0.0001

Data Index: 1257448 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.7677. Min Act: -0.0001

Data Index: 187741 (C4 (Web Text))

Max Activating Token Index: 843