Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2430 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.2302. Min Act: -0.0001

Data Index: 652446 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.2229. Min Act: -0.0001

Data Index: 740974 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.2045. Min Act: -0.0001

Data Index: 228840 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1930. Min Act: -0.0001

Data Index: 297900 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1933. Min Act: -0.0001

Data Index: 1101533 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1927. Min Act: -0.0001

Data Index: 637064 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.2113. Min Act: -0.0001

Data Index: 970927 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1959. Min Act: -0.0001

Data Index: 393043 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1824. Min Act: -0.0001

Data Index: 189659 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1868. Min Act: -0.0001

Data Index: 23141 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1175064 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1791. Min Act: -0.0001

Data Index: 142280 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1776. Min Act: -0.0001

Data Index: 118625 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1694. Min Act: -0.0001

Data Index: 189636 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1759. Min Act: -0.0001

Data Index: 251861 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1749. Min Act: -0.0001

Data Index: 819463 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1674. Min Act: -0.0001

Data Index: 958736 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1737. Min Act: -0.0001

Data Index: 855152 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1727. Min Act: -0.0001

Data Index: 708720 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1602. Min Act: -0.0001

Data Index: 393945 (C4 (Web Text))

Max Activating Token Index: 566