Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1632 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.0266. Min Range: -5.0266

Max Act: 5.0266. Min Act: -0.0001

Data Index: 1169631 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.6295. Min Act: -0.0001

Data Index: 915992 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.4537. Min Act: -0.0001

Data Index: 1040039 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.6019. Min Act: -0.0001

Data Index: 396026 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.3556. Min Act: -0.0001

Data Index: 747109 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.3835. Min Act: -0.0001

Data Index: 195895 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.0505. Min Act: -0.0001

Data Index: 228540 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.0269. Min Act: -0.0001

Data Index: 964231 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 5.0266. Min Range: -5.0266

Max Act: 3.9839. Min Act: -0.0001

Data Index: 1167832 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.1367. Min Act: -0.0001

Data Index: 707917 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 5.0266. Min Range: -5.0266

Max Act: 3.9309. Min Act: -0.0001

Data Index: 570119 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.0762. Min Act: -0.0001

Data Index: 850321 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.1954. Min Act: -0.0001

Data Index: 211297 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 5.0266. Min Range: -5.0266

Max Act: 3.8717. Min Act: -0.0001

Data Index: 149322 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.0098. Min Act: -0.0001

Data Index: 1357467 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 5.0266. Min Range: -5.0266

Max Act: 3.8517. Min Act: -0.0001

Data Index: 343048 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 5.0266. Min Range: -5.0266

Max Act: 4.1130. Min Act: -0.0001

Data Index: 158044 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 5.0266. Min Range: -5.0266

Max Act: 3.7878. Min Act: -0.0001

Data Index: 1176443 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 5.0266. Min Range: -5.0266

Max Act: 3.9209. Min Act: -0.0001

Data Index: 647794 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 5.0266. Min Range: -5.0266

Max Act: 3.6030. Min Act: -0.0001

Data Index: 240819 (C4 (Web Text))

Max Activating Token Index: 253