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

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

Neuron 4156 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7756. Min Act: -0.0000

Data Index: 163952 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7596. Min Act: -0.0000

Data Index: 563708 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1008017 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7805. Min Act: -0.0000

Data Index: 548892 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7573. Min Act: -0.0000

Data Index: 915853 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7459. Min Act: -0.0000

Data Index: 365460 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7247. Min Act: -0.0000

Data Index: 79536 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1127673 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7352. Min Act: -0.0000

Data Index: 863734 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7082. Min Act: -0.0000

Data Index: 227271 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7054. Min Act: -0.0000

Data Index: 214652 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1132411 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7010. Min Act: -0.0000

Data Index: 782224 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1228418 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7154. Min Act: -0.0000

Data Index: 512367 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6718. Min Act: -0.0000

Data Index: 498412 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7132. Min Act: -0.0000

Data Index: 490667 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7091. Min Act: -0.0000

Data Index: 56776 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6621. Min Act: -0.0000

Data Index: 86342 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6821. Min Act: -0.0000

Data Index: 396992 (C4 (Web Text))

Max Activating Token Index: 944