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

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

Neuron 1071 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: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0002

Data Index: 596992 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1056. Min Act: -0.0002

Data Index: 886208 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1050. Min Act: -0.0002

Data Index: 396976 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1019. Min Act: -0.0002

Data Index: 123488 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1019. Min Act: -0.0002

Data Index: 279877 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1031. Min Act: -0.0002

Data Index: 6685 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1202991 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1006. Min Act: -0.0002

Data Index: 200908 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1016. Min Act: -0.0002

Data Index: 431113 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0989. Min Act: -0.0002

Data Index: 220978 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1019. Min Act: -0.0002

Data Index: 490923 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0974. Min Act: -0.0002

Data Index: 287882 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1349492 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1284960 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1295068 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1322311 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1008437 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0978. Min Act: -0.0002

Data Index: 309986 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1117817 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1213372 (C4 (Web Text))

Max Activating Token Index: 674