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

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

Neuron 3760 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2876. Min Range: -2.2876

Max Act: 2.2876. Min Act: -0.0000

Data Index: 1104378 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.8463. Min Act: -0.0000

Data Index: 524080 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 2.2876. Min Range: -2.2876

Max Act: 2.0643. Min Act: -0.0000

Data Index: 662627 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.8697. Min Act: -0.0000

Data Index: 1008713 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.6479. Min Act: -0.0000

Data Index: 800050 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.9121. Min Act: -0.0000

Data Index: 150245 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.7035. Min Act: -0.0000

Data Index: 11593 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.6215. Min Act: -0.0000

Data Index: 1656140 (Python Code)

Max Activating Token Index: 761

Text #8

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.7895. Min Act: -0.0000

Data Index: 1215676 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.6878. Min Act: -0.0000

Data Index: 962695 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.6655. Min Act: -0.0000

Data Index: 1111624 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.6394. Min Act: -0.0000

Data Index: 761270 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.6374. Min Act: -0.0000

Data Index: 449676 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.7152. Min Act: -0.0000

Data Index: 1019424 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.6069. Min Act: -0.0000

Data Index: 1289016 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.5355. Min Act: -0.0000

Data Index: 356695 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.5180. Min Act: -0.0000

Data Index: 1254667 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.6018. Min Act: -0.0000

Data Index: 92205 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.5038. Min Act: -0.0000

Data Index: 559194 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 2.2876. Min Range: -2.2876

Max Act: 1.5228. Min Act: -0.0000

Data Index: 695867 (C4 (Web Text))

Max Activating Token Index: 254