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

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

Neuron 1581 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3047. Min Range: -5.3047

Max Act: 5.2371. Min Act: -0.0000

Data Index: 819863 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 5.3047. Min Range: -5.3047

Max Act: 5.2015. Min Act: -0.0000

Data Index: 1345076 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.9790. Min Act: -0.0000

Data Index: 747684 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.9563. Min Act: -0.0000

Data Index: 892799 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 5.3047. Min Range: -5.3047

Max Act: 5.3047. Min Act: -0.0000

Data Index: 1178499 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.7927. Min Act: -0.0000

Data Index: 601364 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.7832. Min Act: -0.0000

Data Index: 733913 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.5685. Min Act: -0.0000

Data Index: 1224521 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.6792. Min Act: -0.0000

Data Index: 863932 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.5863. Min Act: -0.0000

Data Index: 1027902 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.3391. Min Act: -0.0000

Data Index: 1205450 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.3016. Min Act: -0.0000

Data Index: 748754 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.3782. Min Act: -0.0000

Data Index: 1298760 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.3370. Min Act: -0.0000

Data Index: 583882 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.2911. Min Act: -0.0000

Data Index: 1322090 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.2907. Min Act: -0.0000

Data Index: 969582 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.0269. Min Act: -0.0000

Data Index: 449741 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.2067. Min Act: -0.0000

Data Index: 1115330 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.1982. Min Act: -0.0000

Data Index: 562092 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 5.3047. Min Range: -5.3047

Max Act: 4.1586. Min Act: -0.0000

Data Index: 551162 (C4 (Web Text))

Max Activating Token Index: 314