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

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

Neuron 4246 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4479. Min Range: -7.4479

Max Act: 7.4479. Min Act: -0.0002

Data Index: 22810 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.8096. Min Act: -0.0003

Data Index: 798417 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.6513. Min Act: -0.0003

Data Index: 937782 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.8969. Min Act: -0.0002

Data Index: 91868 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.6804. Min Act: -0.0003

Data Index: 911431 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.6850. Min Act: -0.0002

Data Index: 175772 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.6885. Min Act: -0.0003

Data Index: 817281 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.6812. Min Act: -0.0003

Data Index: 341706 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.6332. Min Act: -0.0003

Data Index: 810740 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.4464. Min Act: -0.0003

Data Index: 833961 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.6104. Min Act: -0.0002

Data Index: 1029919 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.5773. Min Act: -0.0003

Data Index: 1158931 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.5706. Min Act: -0.0003

Data Index: 60282 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.5614. Min Act: -0.0002

Data Index: 425473 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.5475. Min Act: -0.0003

Data Index: 35478 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.5310. Min Act: -0.0003

Data Index: 786970 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.5303. Min Act: -0.0002

Data Index: 610998 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.6837. Min Act: -0.0002

Data Index: 1165870 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.5185. Min Act: -0.0002

Data Index: 1097409 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 7.4479. Min Range: -7.4479

Max Act: 6.4614. Min Act: -0.0002

Data Index: 1126524 (C4 (Web Text))

Max Activating Token Index: 694