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

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

Neuron 48 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9923. Min Act: -0.0002

Data Index: 1314535 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9596. Min Act: -0.0002

Data Index: 1063521 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9596. Min Act: -0.0002

Data Index: 421702 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9272. Min Act: -0.0002

Data Index: 658721 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9297. Min Act: -0.0002

Data Index: 1210313 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9191. Min Act: -0.0002

Data Index: 101097 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9266. Min Act: -0.0002

Data Index: 1003719 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9174. Min Act: -0.0002

Data Index: 550915 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8901. Min Act: -0.0002

Data Index: 485536 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9094. Min Act: -0.0002

Data Index: 1244160 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8840. Min Act: -0.0002

Data Index: 486534 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8880. Min Act: -0.0002

Data Index: 850166 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8937. Min Act: -0.0002

Data Index: 485472 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8801. Min Act: -0.0002

Data Index: 645615 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8642. Min Act: -0.0002

Data Index: 668940 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8871. Min Act: -0.0002

Data Index: 990352 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8623. Min Act: -0.0002

Data Index: 655483 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8487. Min Act: -0.0002

Data Index: 941200 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8602. Min Act: -0.0002

Data Index: 779643 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8629. Min Act: -0.0002

Data Index: 875505 (C4 (Web Text))

Max Activating Token Index: 14