Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3664 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.3615. Min Act: -0.0001

Data Index: 1246828 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.3512. Min Act: -0.0001

Data Index: 14040 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.2865. Min Act: -0.0001

Data Index: 737609 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.1991. Min Act: -0.0001

Data Index: 507645 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.2092. Min Act: -0.0001

Data Index: 809616 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.2387. Min Act: -0.0001

Data Index: 1213682 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.1888. Min Act: -0.0001

Data Index: 172413 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.2133. Min Act: -0.0001

Data Index: 1165843 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.2486. Min Act: -0.0001

Data Index: 167305 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.1171. Min Act: -0.0001

Data Index: 384616 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.1640. Min Act: -0.0001

Data Index: 67062 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0835. Min Act: -0.0001

Data Index: 1128427 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0811. Min Act: -0.0001

Data Index: 193907 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0725. Min Act: -0.0001

Data Index: 1121287 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.1484. Min Act: -0.0001

Data Index: 931023 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0673. Min Act: -0.0001

Data Index: 465472 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.1231. Min Act: -0.0001

Data Index: 897903 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0866. Min Act: -0.0001

Data Index: 187452 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.1223. Min Act: -0.0001

Data Index: 34960 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0516. Min Act: -0.0001

Data Index: 965831 (C4 (Web Text))

Max Activating Token Index: 934