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

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

Neuron 784 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: 0.1043. Min Range: -0.1043

Max Act: 0.1043. Min Act: -0.0002

Data Index: 563107 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1001. Min Act: -0.0001

Data Index: 355003 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0990. Min Act: -0.0002

Data Index: 244758 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0929. Min Act: -0.0002

Data Index: 352970 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0897. Min Act: -0.0002

Data Index: 198088 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0870. Min Act: -0.0002

Data Index: 182910 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0879. Min Act: -0.0002

Data Index: 677294 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1092939 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0903. Min Act: -0.0002

Data Index: 757636 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0906. Min Act: -0.0002

Data Index: 43924 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1193164 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0881. Min Act: -0.0002

Data Index: 852038 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0825. Min Act: -0.0002

Data Index: 136014 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0845. Min Act: -0.0002

Data Index: 402142 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0808. Min Act: -0.0002

Data Index: 143605 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0807. Min Act: -0.0002

Data Index: 776153 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0791. Min Act: -0.0002

Data Index: 454941 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1227266 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0804. Min Act: -0.0002

Data Index: 454330 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1334421 (C4 (Web Text))

Max Activating Token Index: 820