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

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

Neuron 4411 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.6007. Min Act: -0.0000

Data Index: 1029420 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.4503. Min Act: -0.0000

Data Index: 866697 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1117081 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.2859. Min Act: -0.0000

Data Index: 627058 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.1195. Min Act: -0.0000

Data Index: 889320 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1051172 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.0876. Min Act: -0.0000

Data Index: 365292 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.0785. Min Act: -0.0000

Data Index: 186073 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1055974 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.0671. Min Act: -0.0000

Data Index: 866500 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.0632. Min Act: -0.0000

Data Index: 286269 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1027365 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 1.6007. Min Range: -1.6007

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1327195 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 1.6007. Min Range: -1.6007

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1209703 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 1.6007. Min Range: -1.6007

Max Act: 0.9229. Min Act: -0.0000

Data Index: 881119 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 1.6007. Min Range: -1.6007

Max Act: 0.9241. Min Act: -0.0000

Data Index: 319832 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.6007. Min Range: -1.6007

Max Act: 0.9798. Min Act: -0.0000

Data Index: 676224 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 1.6007. Min Range: -1.6007

Max Act: 0.9090. Min Act: -0.0000

Data Index: 196227 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.6007. Min Range: -1.6007

Max Act: 0.9687. Min Act: -0.0000

Data Index: 97789 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 1.6007. Min Range: -1.6007

Max Act: 0.9607. Min Act: -0.0000

Data Index: 734752 (C4 (Web Text))

Max Activating Token Index: 826