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

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

Neuron 2023 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.7036. Min Act: 0.0001

Data Index: 560332 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.6122. Min Act: -0.0000

Data Index: 628224 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3618. Min Act: -0.0000

Data Index: 285401 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.2765. Min Act: 0.0001

Data Index: 116769 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.2055. Min Act: 0.0001

Data Index: 1347855 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.2204. Min Act: -0.0000

Data Index: 171674 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.1376. Min Act: 0.0000

Data Index: 692975 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.1112. Min Act: -0.0000

Data Index: 536774 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.0636. Min Act: -0.0000

Data Index: 370002 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.0505. Min Act: 0.0000

Data Index: 1260695 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 1.7036. Min Range: -1.7036

Max Act: 0.9798. Min Act: -0.0000

Data Index: 285980 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 1.7036. Min Range: -1.7036

Max Act: 0.9787. Min Act: -0.0000

Data Index: 698165 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 1.7036. Min Range: -1.7036

Max Act: 0.9552. Min Act: 0.0001

Data Index: 229219 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 1.7036. Min Range: -1.7036

Max Act: 0.9462. Min Act: -0.0000

Data Index: 38209 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 1.7036. Min Range: -1.7036

Max Act: 0.9338. Min Act: -0.0000

Data Index: 787808 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 1.7036. Min Range: -1.7036

Max Act: 0.9303. Min Act: 0.0001

Data Index: 1097732 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.7036. Min Range: -1.7036

Max Act: 0.9244. Min Act: 0.0000

Data Index: 831007 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 1.7036. Min Range: -1.7036

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1094465 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 1.7036. Min Range: -1.7036

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1029079 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 1.7036. Min Range: -1.7036

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1136873 (C4 (Web Text))

Max Activating Token Index: 547