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

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

Neuron 4717 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: 0.8589. Min Range: -0.8589

Max Act: 0.8589. Min Act: -0.0000

Data Index: 141656 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.7849. Min Act: -0.0000

Data Index: 704303 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6977. Min Act: -0.0000

Data Index: 281393 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.7237. Min Act: -0.0000

Data Index: 397967 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.7488. Min Act: -0.0000

Data Index: 679164 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6948. Min Act: 0.0000

Data Index: 653094 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6764. Min Act: -0.0000

Data Index: 348091 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1047699 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6352. Min Act: -0.0000

Data Index: 360937 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1162131 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6465. Min Act: -0.0000

Data Index: 466974 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6059. Min Act: -0.0000

Data Index: 557982 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6172. Min Act: 0.0001

Data Index: 622714 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.5818. Min Act: -0.0000

Data Index: 542757 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.5872. Min Act: -0.0000

Data Index: 975980 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1181625 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.5636. Min Act: -0.0000

Data Index: 174885 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.5540. Min Act: -0.0000

Data Index: 176165 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.5685. Min Act: -0.0000

Data Index: 186961 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.5523. Min Act: -0.0000

Data Index: 348070 (C4 (Web Text))

Max Activating Token Index: 811