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

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

Neuron 3828 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3297. Min Range: -6.3297

Max Act: 6.3297. Min Act: -0.0000

Data Index: 957152 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 6.3297. Min Range: -6.3297

Max Act: 5.9761. Min Act: -0.0000

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 6.3297. Min Range: -6.3297

Max Act: 5.7939. Min Act: -0.0000

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 6.3297. Min Range: -6.3297

Max Act: 5.3117. Min Act: -0.0000

Data Index: 144215 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 6.3297. Min Range: -6.3297

Max Act: 5.0877. Min Act: -0.0000

Data Index: 889261 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 6.3297. Min Range: -6.3297

Max Act: 5.4109. Min Act: -0.0000

Data Index: 319736 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 6.3297. Min Range: -6.3297

Max Act: 5.1477. Min Act: -0.0000

Data Index: 1067596 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 6.3297. Min Range: -6.3297

Max Act: 5.2638. Min Act: -0.0000

Data Index: 406250 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 6.3297. Min Range: -6.3297

Max Act: 5.2191. Min Act: -0.0000

Data Index: 609223 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 6.3297. Min Range: -6.3297

Max Act: 5.0387. Min Act: -0.0000

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 6.3297. Min Range: -6.3297

Max Act: 4.9506. Min Act: -0.0000

Data Index: 829079 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 6.3297. Min Range: -6.3297

Max Act: 4.7126. Min Act: -0.0000

Data Index: 949699 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 6.3297. Min Range: -6.3297

Max Act: 4.5122. Min Act: -0.0000

Data Index: 843970 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 6.3297. Min Range: -6.3297

Max Act: 4.6240. Min Act: -0.0000

Data Index: 732373 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 6.3297. Min Range: -6.3297

Max Act: 4.5650. Min Act: -0.0000

Data Index: 684922 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 6.3297. Min Range: -6.3297

Max Act: 4.7007. Min Act: -0.0000

Data Index: 33870 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 6.3297. Min Range: -6.3297

Max Act: 4.3849. Min Act: -0.0000

Data Index: 434820 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 6.3297. Min Range: -6.3297

Max Act: 4.4921. Min Act: -0.0000

Data Index: 1071860 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 6.3297. Min Range: -6.3297

Max Act: 4.2899. Min Act: -0.0000

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 6.3297. Min Range: -6.3297

Max Act: 4.3080. Min Act: -0.0000

Data Index: 446463 (C4 (Web Text))

Max Activating Token Index: 722