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

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

Neuron 76 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.8824. Min Act: -0.0000

Data Index: 244491 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.8611. Min Act: -0.0001

Data Index: 823238 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.8265. Min Act: -0.0000

Data Index: 166661 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7513. Min Act: -0.0000

Data Index: 62453 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7344. Min Act: -0.0000

Data Index: 348216 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6922. Min Act: -0.0001

Data Index: 907957 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6968. Min Act: -0.0000

Data Index: 586715 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6826. Min Act: -0.0000

Data Index: 679204 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6719. Min Act: -0.0001

Data Index: 344080 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6810. Min Act: -0.0000

Data Index: 412045 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6349. Min Act: -0.0001

Data Index: 157911 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1060041 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1178797 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6378. Min Act: -0.0000

Data Index: 88209 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1033198 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6096. Min Act: -0.0001

Data Index: 578668 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6231. Min Act: -0.0000

Data Index: 662176 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6219. Min Act: -0.0001

Data Index: 1123519 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6363. Min Act: -0.0000

Data Index: 503890 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.5537. Min Act: -0.0000

Data Index: 367639 (C4 (Web Text))

Max Activating Token Index: 350