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

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

Neuron 3548 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1156. Min Act: -0.0002

Data Index: 88799 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1023. Min Act: -0.0001

Data Index: 743941 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1013. Min Act: -0.0001

Data Index: 846152 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0953. Min Act: -0.0002

Data Index: 177246 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0902. Min Act: -0.0002

Data Index: 553182 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0777. Min Act: -0.0002

Data Index: 584008 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0871. Min Act: -0.0002

Data Index: 740248 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0868. Min Act: -0.0001

Data Index: 925463 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0801. Min Act: -0.0002

Data Index: 909370 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0791. Min Act: -0.0001

Data Index: 756275 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0749. Min Act: -0.0001

Data Index: 220305 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0741. Min Act: -0.0002

Data Index: 478036 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0720. Min Act: -0.0002

Data Index: 871650 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1019612 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0689. Min Act: -0.0001

Data Index: 189701 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1160488 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0653. Min Act: -0.0002

Data Index: 689996 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0681. Min Act: -0.0001

Data Index: 317157 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1268438 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0675. Min Act: -0.0002

Data Index: 502741 (C4 (Web Text))

Max Activating Token Index: 533