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

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

Neuron 2240 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2628. Min Act: -0.0000

Data Index: 401717 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2530. Min Act: -0.0001

Data Index: 215073 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2516. Min Act: -0.0001

Data Index: 13894 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1284672 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1922. Min Act: -0.0001

Data Index: 651692 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2092. Min Act: -0.0001

Data Index: 49528 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1978. Min Act: -0.0000

Data Index: 407102 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1870. Min Act: -0.0001

Data Index: 750448 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1090625 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1844. Min Act: -0.0001

Data Index: 1320187 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1964. Min Act: -0.0001

Data Index: 229420 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1933. Min Act: -0.0000

Data Index: 911492 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1890. Min Act: -0.0000

Data Index: 361658 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1823. Min Act: -0.0001

Data Index: 293285 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1898. Min Act: -0.0001

Data Index: 416452 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1787. Min Act: -0.0001

Data Index: 867178 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1067866 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1808. Min Act: -0.0000

Data Index: 993166 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1934. Min Act: -0.0001

Data Index: 37578 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1766. Min Act: -0.0001

Data Index: 737395 (C4 (Web Text))

Max Activating Token Index: 400