Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 512 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1195. Min Act: -0.0002

Data Index: 790091 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1049028 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1217324 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0973. Min Act: -0.0002

Data Index: 487777 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0929. Min Act: -0.0002

Data Index: 295866 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1015. Min Act: -0.0002

Data Index: 105805 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0943. Min Act: -0.0002

Data Index: 339612 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0906. Min Act: -0.0002

Data Index: 381126 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0930. Min Act: -0.0002

Data Index: 668552 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0927. Min Act: -0.0002

Data Index: 192268 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0921. Min Act: -0.0002

Data Index: 309521 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1128407 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0870. Min Act: -0.0002

Data Index: 612950 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0845. Min Act: -0.0002

Data Index: 130505 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0872. Min Act: -0.0002

Data Index: 926309 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0850. Min Act: -0.0002

Data Index: 940245 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0863. Min Act: -0.0002

Data Index: 900532 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0873. Min Act: -0.0002

Data Index: 348625 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1095770 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0784. Min Act: -0.0002

Data Index: 806824 (C4 (Web Text))

Max Activating Token Index: 317