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

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

Neuron 3272 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.1758. Min Act: -0.0000

Data Index: 993440 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.4558. Min Act: -0.0000

Data Index: 358364 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.3041. Min Act: -0.0000

Data Index: 1218840 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.1117. Min Act: -0.0000

Data Index: 1057758 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.0849. Min Act: -0.0000

Data Index: 1072052 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.1202. Min Act: -0.0000

Data Index: 673200 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.7923. Min Act: -0.0000

Data Index: 1132706 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.7722. Min Act: -0.0000

Data Index: 581989 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.8736. Min Act: -0.0000

Data Index: 551616 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.7359. Min Act: -0.0000

Data Index: 916266 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.5313. Min Act: -0.0000

Data Index: 406966 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.6488. Min Act: -0.0000

Data Index: 482931 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.5737. Min Act: -0.0000

Data Index: 895943 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.5757. Min Act: -0.0000

Data Index: 175678 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.5272. Min Act: -0.0000

Data Index: 341056 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.5574. Min Act: -0.0000

Data Index: 1266341 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.5495. Min Act: -0.0000

Data Index: 1298870 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.4346. Min Act: -0.0000

Data Index: 261420 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.5657. Min Act: -0.0000

Data Index: 1162021 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 3.1758. Min Range: -3.1758

Max Act: 1.5044. Min Act: -0.0000

Data Index: 809161 (C4 (Web Text))

Max Activating Token Index: 754