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

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

Neuron 6133 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7996. Min Range: -4.7996

Max Act: 4.7996. Min Act: -0.0000

Data Index: 1247765 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 4.7996. Min Range: -4.7996

Max Act: 4.7198. Min Act: -0.0000

Data Index: 1022404 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 4.7996. Min Range: -4.7996

Max Act: 4.7443. Min Act: -0.0000

Data Index: 246916 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 4.7996. Min Range: -4.7996

Max Act: 4.4675. Min Act: -0.0000

Data Index: 538750 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 4.7996. Min Range: -4.7996

Max Act: 4.1421. Min Act: -0.0000

Data Index: 1203735 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.9005. Min Act: -0.0000

Data Index: 681151 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.8029. Min Act: -0.0000

Data Index: 908264 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.5261. Min Act: -0.0000

Data Index: 208993 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.3337. Min Act: -0.0000

Data Index: 1165729 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.2809. Min Act: -0.0000

Data Index: 174570 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.0863. Min Act: -0.0000

Data Index: 178645 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.0244. Min Act: -0.0000

Data Index: 1041337 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.0200. Min Act: -0.0000

Data Index: 516169 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.1819. Min Act: -0.0000

Data Index: 264315 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.0094. Min Act: -0.0000

Data Index: 671287 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.1379. Min Act: -0.0000

Data Index: 1175553 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.1055. Min Act: -0.0000

Data Index: 704116 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.2301. Min Act: -0.0000

Data Index: 623982 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.0016. Min Act: -0.0000

Data Index: 1044284 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 4.7996. Min Range: -4.7996

Max Act: 3.1518. Min Act: -0.0000

Data Index: 520658 (C4 (Web Text))

Max Activating Token Index: 990