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

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

Neuron 5821 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: 0.1137. Min Range: -0.1137

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1045638 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1105. Min Act: -0.0002

Data Index: 549026 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1092. Min Act: -0.0002

Data Index: 149172 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0995. Min Act: -0.0002

Data Index: 37371 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0975. Min Act: -0.0002

Data Index: 638118 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1105942 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0932. Min Act: -0.0002

Data Index: 710779 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0944. Min Act: -0.0002

Data Index: 902931 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0916. Min Act: -0.0002

Data Index: 298613 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1178898 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0931. Min Act: -0.0002

Data Index: 413926 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0872. Min Act: -0.0002

Data Index: 128729 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0827. Min Act: -0.0002

Data Index: 479262 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1303818 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0842. Min Act: -0.0002

Data Index: 918624 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0836. Min Act: -0.0002

Data Index: 933707 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0812. Min Act: -0.0002

Data Index: 188205 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0833. Min Act: -0.0002

Data Index: 139646 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0836. Min Act: -0.0002

Data Index: 105157 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0801. Min Act: -0.0002

Data Index: 954596 (C4 (Web Text))

Max Activating Token Index: 751