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

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

Neuron 3471 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1890. Min Range: -2.1890

Max Act: 2.1890. Min Act: -0.0000

Data Index: 295826 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 2.1890. Min Range: -2.1890

Max Act: 2.0216. Min Act: -0.0000

Data Index: 1142239 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 2.1890. Min Range: -2.1890

Max Act: 2.0189. Min Act: -0.0000

Data Index: 383029 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.9181. Min Act: -0.0000

Data Index: 757112 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.8171. Min Act: -0.0000

Data Index: 221450 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.9221. Min Act: -0.0000

Data Index: 1096236 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.7375. Min Act: -0.0000

Data Index: 1300914 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.6151. Min Act: -0.0000

Data Index: 1197922 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.7223. Min Act: -0.0000

Data Index: 23373 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.7999. Min Act: -0.0001

Data Index: 976123 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.6936. Min Act: -0.0000

Data Index: 1060051 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.6772. Min Act: -0.0000

Data Index: 793092 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.6478. Min Act: -0.0001

Data Index: 1012894 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.6184. Min Act: -0.0000

Data Index: 195230 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.5678. Min Act: -0.0000

Data Index: 726011 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.4071. Min Act: -0.0000

Data Index: 129280 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.5443. Min Act: -0.0000

Data Index: 1055910 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.5245. Min Act: -0.0000

Data Index: 895216 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.7030. Min Act: -0.0000

Data Index: 1141830 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 2.1890. Min Range: -2.1890

Max Act: 1.6169. Min Act: -0.0000

Data Index: 365518 (C4 (Web Text))

Max Activating Token Index: 703