Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1154 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0814. Min Act: -0.0003

Data Index: 1035394 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0826. Min Act: -0.0003

Data Index: 678146 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0720. Min Act: -0.0003

Data Index: 762532 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0728. Min Act: -0.0003

Data Index: 577020 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0709. Min Act: -0.0003

Data Index: 667006 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0684. Min Act: -0.0003

Data Index: 47675 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1038029 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0751. Min Act: -0.0003

Data Index: 853975 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1180622 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1340114 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0662. Min Act: -0.0003

Data Index: 354018 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0634. Min Act: -0.0003

Data Index: 795455 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0664. Min Act: -0.0003

Data Index: 281612 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1085623 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0645. Min Act: -0.0003

Data Index: 788703 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0630. Min Act: -0.0003

Data Index: 325149 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1208451 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0543. Min Act: -0.0003

Data Index: 522533 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0590. Min Act: -0.0003

Data Index: 745271 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0636. Min Act: -0.0003

Data Index: 212379 (C4 (Web Text))

Max Activating Token Index: 672