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

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

Neuron 461 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: 2.6780. Min Range: -2.6780

Max Act: 2.6780. Min Act: -0.0000

Data Index: 362995 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.3412. Min Act: -0.0000

Data Index: 1243308 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.9184. Min Act: -0.0000

Data Index: 1162117 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.9394. Min Act: -0.0000

Data Index: 1348165 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.9097. Min Act: -0.0000

Data Index: 58695 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.8247. Min Act: -0.0000

Data Index: 614972 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.7162. Min Act: -0.0000

Data Index: 899677 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.5938. Min Act: -0.0000

Data Index: 1060182 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.5979. Min Act: -0.0000

Data Index: 992258 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.5843. Min Act: -0.0000

Data Index: 360941 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.6751. Min Act: -0.0000

Data Index: 1231644 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.4894. Min Act: -0.0000

Data Index: 456291 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.5240. Min Act: -0.0000

Data Index: 501491 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.5024. Min Act: -0.0000

Data Index: 955028 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.4862. Min Act: -0.0000

Data Index: 134130 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.5699. Min Act: -0.0000

Data Index: 197415 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.3793. Min Act: -0.0000

Data Index: 713609 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.4732. Min Act: -0.0000

Data Index: 1319133 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.5540. Min Act: -0.0000

Data Index: 967189 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.4395. Min Act: -0.0000

Data Index: 224620 (C4 (Web Text))

Max Activating Token Index: 406