Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 55 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.3994. Min Act: -0.0000

Data Index: 910673 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.4473. Min Act: -0.0000

Data Index: 424783 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.9265. Min Act: -0.0000

Data Index: 666535 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.8771. Min Act: -0.0000

Data Index: 1195536 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.8261. Min Act: -0.0000

Data Index: 419017 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.8858. Min Act: -0.0000

Data Index: 1026767 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.8631. Min Act: -0.0000

Data Index: 1089895 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.8132. Min Act: -0.0000

Data Index: 783855 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.8322. Min Act: -0.0000

Data Index: 1156901 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.8008. Min Act: -0.0000

Data Index: 1101578 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.7498. Min Act: -0.0000

Data Index: 1216239 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.6501. Min Act: -0.0000

Data Index: 513908 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.6149. Min Act: -0.0000

Data Index: 1258852 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.4801. Min Act: -0.0000

Data Index: 13955 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.5057. Min Act: -0.0000

Data Index: 1216242 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.4939. Min Act: -0.0000

Data Index: 497539 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.5011. Min Act: -0.0000

Data Index: 694658 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.3723. Min Act: -0.0000

Data Index: 738785 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.3175. Min Act: -0.0000

Data Index: 422598 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 3.4473. Min Range: -3.4473

Max Act: 2.4375. Min Act: -0.0000

Data Index: 1004451 (C4 (Web Text))

Max Activating Token Index: 565