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

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

Neuron 4351 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: 9.5501. Min Range: -9.5501

Max Act: 9.5501. Min Act: -0.0000

Data Index: 373968 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 9.5501. Min Range: -9.5501

Max Act: 9.4003. Min Act: -0.0000

Data Index: 579528 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 9.5501. Min Range: -9.5501

Max Act: 9.1451. Min Act: -0.0000

Data Index: 466253 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 9.5501. Min Range: -9.5501

Max Act: 8.3539. Min Act: -0.0000

Data Index: 486401 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 9.5501. Min Range: -9.5501

Max Act: 8.3398. Min Act: -0.0000

Data Index: 234569 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 9.5501. Min Range: -9.5501

Max Act: 8.2891. Min Act: -0.0000

Data Index: 1042910 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 9.5501. Min Range: -9.5501

Max Act: 8.1319. Min Act: -0.0000

Data Index: 305772 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 9.5501. Min Range: -9.5501

Max Act: 8.2552. Min Act: -0.0000

Data Index: 652815 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 9.5501. Min Range: -9.5501

Max Act: 8.0111. Min Act: -0.0000

Data Index: 1232060 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 9.5501. Min Range: -9.5501

Max Act: 8.1794. Min Act: -0.0000

Data Index: 677913 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 9.5501. Min Range: -9.5501

Max Act: 8.0928. Min Act: -0.0000

Data Index: 479156 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 9.5501. Min Range: -9.5501

Max Act: 7.8607. Min Act: -0.0000

Data Index: 269433 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 9.5501. Min Range: -9.5501

Max Act: 7.7027. Min Act: -0.0000

Data Index: 486877 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 9.5501. Min Range: -9.5501

Max Act: 7.7043. Min Act: -0.0000

Data Index: 1153890 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 9.5501. Min Range: -9.5501

Max Act: 7.4959. Min Act: -0.0000

Data Index: 304808 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 9.5501. Min Range: -9.5501

Max Act: 7.6501. Min Act: -0.0000

Data Index: 791027 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 9.5501. Min Range: -9.5501

Max Act: 7.6652. Min Act: -0.0000

Data Index: 283810 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 9.5501. Min Range: -9.5501

Max Act: 7.6566. Min Act: -0.0000

Data Index: 402376 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 9.5501. Min Range: -9.5501

Max Act: 7.8207. Min Act: -0.0000

Data Index: 1223703 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 9.5501. Min Range: -9.5501

Max Act: 7.7445. Min Act: -0.0000

Data Index: 1279928 (C4 (Web Text))

Max Activating Token Index: 73