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

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

Neuron 4781 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: 0.2948. Min Range: -0.2948

Max Act: 0.2656. Min Act: -0.0002

Data Index: 108934 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2948. Min Act: -0.0002

Data Index: 1254902 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2806. Min Act: -0.0002

Data Index: 481710 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2655. Min Act: -0.0002

Data Index: 772337 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2623. Min Act: -0.0002

Data Index: 1047928 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2590. Min Act: -0.0002

Data Index: 1325667 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2618. Min Act: -0.0002

Data Index: 871077 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2549. Min Act: -0.0002

Data Index: 737026 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2518. Min Act: -0.0002

Data Index: 129998 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2147. Min Act: -0.0002

Data Index: 1018642 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2546. Min Act: -0.0002

Data Index: 954811 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2504. Min Act: -0.0002

Data Index: 611561 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2124. Min Act: -0.0002

Data Index: 720251 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2355. Min Act: -0.0002

Data Index: 296772 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2118. Min Act: -0.0002

Data Index: 1250863 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1942. Min Act: -0.0002

Data Index: 375878 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1997. Min Act: -0.0002

Data Index: 1231791 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1918. Min Act: -0.0002

Data Index: 58834 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1720. Min Act: -0.0002

Data Index: 750209 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1870. Min Act: -0.0002

Data Index: 281360 (C4 (Web Text))

Max Activating Token Index: 377