Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2770 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1092. Min Act: -0.0002

Data Index: 883283 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1063. Min Act: -0.0002

Data Index: 498234 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1050845 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1184524 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0923. Min Act: -0.0002

Data Index: 62521 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0928. Min Act: -0.0002

Data Index: 161558 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0923. Min Act: -0.0002

Data Index: 780379 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0915. Min Act: -0.0002

Data Index: 665560 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0915. Min Act: -0.0002

Data Index: 65431 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0855. Min Act: -0.0002

Data Index: 409160 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1312869 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0835. Min Act: -0.0002

Data Index: 357228 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1100230 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0834. Min Act: -0.0002

Data Index: 446696 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1053156 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0825. Min Act: -0.0002

Data Index: 445484 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1206940 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0793. Min Act: -0.0002

Data Index: 696659 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0834. Min Act: -0.0002

Data Index: 934166 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1251752 (C4 (Web Text))

Max Activating Token Index: 209