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

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

Neuron 1122 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1008993 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1053956 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6739. Min Act: -0.0001

Data Index: 997908 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6853. Min Act: -0.0000

Data Index: 294125 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6351. Min Act: -0.0000

Data Index: 888094 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6084. Min Act: -0.0000

Data Index: 186879 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6202. Min Act: -0.0000

Data Index: 644016 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6367. Min Act: -0.0000

Data Index: 273116 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1289984 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6327. Min Act: -0.0000

Data Index: 130372 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6067. Min Act: -0.0000

Data Index: 885039 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5740. Min Act: -0.0001

Data Index: 702950 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5723. Min Act: -0.0000

Data Index: 415506 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6534. Min Act: -0.0000

Data Index: 183361 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5780. Min Act: -0.0000

Data Index: 700553 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1152782 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5969. Min Act: -0.0000

Data Index: 869855 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1351805 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5322. Min Act: -0.0000

Data Index: 990001 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5536. Min Act: -0.0000

Data Index: 552617 (C4 (Web Text))

Max Activating Token Index: 886