Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2814 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.7196. Min Act: -0.0001

Data Index: 344705 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6971. Min Act: -0.0002

Data Index: 1123987 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.7005. Min Act: -0.0002

Data Index: 56027 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.7225. Min Act: -0.0002

Data Index: 1174734 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.7166. Min Act: -0.0002

Data Index: 868758 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6662. Min Act: -0.0001

Data Index: 887655 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1481000 (Python Code)

Max Activating Token Index: 261

Text #7

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6964. Min Act: -0.0002

Data Index: 730622 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6679. Min Act: -0.0002

Data Index: 304869 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6685. Min Act: -0.0001

Data Index: 210109 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6830. Min Act: -0.0002

Data Index: 1222427 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6399. Min Act: -0.0002

Data Index: 302514 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6110. Min Act: -0.0002

Data Index: 20053 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6502. Min Act: -0.0002

Data Index: 484111 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6366. Min Act: -0.0002

Data Index: 123095 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5457. Min Act: -0.0001

Data Index: 450414 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5881. Min Act: -0.0001

Data Index: 997890 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6001. Min Act: -0.0002

Data Index: 87877 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6250. Min Act: -0.0002

Data Index: 517972 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6492. Min Act: -0.0002

Data Index: 420646 (C4 (Web Text))

Max Activating Token Index: 87