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

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

Neuron 3655 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0378. Min Range: -1.0378

Max Act: 1.0378. Min Act: -0.0000

Data Index: 720587 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7252. Min Act: -0.0000

Data Index: 689518 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7662. Min Act: -0.0000

Data Index: 673229 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6852. Min Act: -0.0000

Data Index: 888924 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7242. Min Act: 0.0000

Data Index: 460590 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7982. Min Act: -0.0000

Data Index: 827137 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7204. Min Act: -0.0000

Data Index: 979699 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6711. Min Act: -0.0000

Data Index: 500714 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6954. Min Act: 0.0000

Data Index: 260695 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6683. Min Act: -0.0000

Data Index: 213823 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6592. Min Act: -0.0000

Data Index: 654594 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7036. Min Act: -0.0000

Data Index: 659518 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6457. Min Act: -0.0000

Data Index: 132002 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6585. Min Act: -0.0000

Data Index: 642989 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1205583 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6049. Min Act: -0.0000

Data Index: 155957 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6228. Min Act: -0.0000

Data Index: 940196 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6560. Min Act: -0.0000

Data Index: 6094 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6373. Min Act: -0.0000

Data Index: 835205 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.5745. Min Act: -0.0000

Data Index: 824100 (C4 (Web Text))

Max Activating Token Index: 558