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

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

Neuron 5648 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8599. Min Range: -4.8599

Max Act: 4.8599. Min Act: -0.0001

Data Index: 564241 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 4.8599. Min Range: -4.8599

Max Act: 4.1936. Min Act: -0.0001

Data Index: 828382 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 4.8599. Min Range: -4.8599

Max Act: 4.3612. Min Act: -0.0001

Data Index: 62823 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 4.8599. Min Range: -4.8599

Max Act: 4.5544. Min Act: -0.0001

Data Index: 1284547 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 4.8599. Min Range: -4.8599

Max Act: 4.1723. Min Act: -0.0001

Data Index: 1064494 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.9998. Min Act: -0.0001

Data Index: 772891 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.8466. Min Act: -0.0001

Data Index: 155387 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.9958. Min Act: -0.0001

Data Index: 298758 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 4.8599. Min Range: -4.8599

Max Act: 4.1194. Min Act: -0.0001

Data Index: 65692 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.6007. Min Act: -0.0001

Data Index: 768917 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.9241. Min Act: -0.0001

Data Index: 1077277 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.6077. Min Act: -0.0001

Data Index: 864983 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.7295. Min Act: -0.0001

Data Index: 388324 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.7010. Min Act: -0.0001

Data Index: 551936 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 4.8599. Min Range: -4.8599

Max Act: 4.0470. Min Act: -0.0001

Data Index: 653039 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 4.8599. Min Range: -4.8599

Max Act: 4.0063. Min Act: -0.0001

Data Index: 823935 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.6384. Min Act: -0.0001

Data Index: 386765 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.6224. Min Act: -0.0001

Data Index: 179910 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.7612. Min Act: -0.0001

Data Index: 7842 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 4.8599. Min Range: -4.8599

Max Act: 3.3546. Min Act: -0.0001

Data Index: 653598 (C4 (Web Text))

Max Activating Token Index: 189