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

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

Neuron 5297 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: 1.1146. Min Range: -1.1146

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1011242 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.1146. Min Range: -1.1146

Max Act: 1.1012. Min Act: -0.0000

Data Index: 435859 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.1146. Min Range: -1.1146

Max Act: 1.1146. Min Act: -0.0000

Data Index: 235338 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.1146. Min Range: -1.1146

Max Act: 1.0108. Min Act: -0.0000

Data Index: 1426915 (Python Code)

Max Activating Token Index: 975

Text #4

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.9972. Min Act: -0.0000

Data Index: 340802 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 1.1146. Min Range: -1.1146

Max Act: 1.0537. Min Act: -0.0000

Data Index: 557199 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.9170. Min Act: -0.0000

Data Index: 442333 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.9597. Min Act: -0.0000

Data Index: 392980 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.9425. Min Act: -0.0000

Data Index: 738456 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8787. Min Act: -0.0000

Data Index: 504477 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8837. Min Act: -0.0000

Data Index: 510370 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.9478. Min Act: -0.0000

Data Index: 158953 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1262024 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8196. Min Act: -0.0000

Data Index: 646971 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8758. Min Act: -0.0000

Data Index: 945999 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8832. Min Act: -0.0000

Data Index: 16636 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8587. Min Act: -0.0000

Data Index: 609904 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8944. Min Act: -0.0000

Data Index: 147872 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8983. Min Act: -0.0000

Data Index: 311781 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8571. Min Act: -0.0000

Data Index: 75047 (C4 (Web Text))

Max Activating Token Index: 843