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

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

Neuron 4382 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2720. Min Act: -0.0000

Data Index: 579287 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2304. Min Act: -0.0000

Data Index: 137703 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1216546 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2092. Min Act: -0.0000

Data Index: 283194 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2097. Min Act: 0.0000

Data Index: 791939 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2071. Min Act: -0.0000

Data Index: 420770 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1019157 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1950. Min Act: -0.0000

Data Index: 953151 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1252285 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1924. Min Act: 0.0000

Data Index: 1105800 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1946. Min Act: -0.0000

Data Index: 855834 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1830. Min Act: 0.0002

Data Index: 167181 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1759. Min Act: -0.0000

Data Index: 595783 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1741. Min Act: -0.0000

Data Index: 423620 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1762. Min Act: -0.0000

Data Index: 959486 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1671. Min Act: -0.0000

Data Index: 398272 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1719. Min Act: 0.0001

Data Index: 1132472 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1204063 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1195111 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1222714 (C4 (Web Text))

Max Activating Token Index: 648