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

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

Neuron 102 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7190. Min Range: -7.7190

Max Act: 7.7190. Min Act: -0.0000

Data Index: 836695 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 7.7190. Min Range: -7.7190

Max Act: 7.3752. Min Act: -0.0000

Data Index: 749506 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 7.7190. Min Range: -7.7190

Max Act: 7.4694. Min Act: -0.0000

Data Index: 1180160 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 7.7190. Min Range: -7.7190

Max Act: 7.5591. Min Act: -0.0000

Data Index: 724909 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.8380. Min Act: -0.0000

Data Index: 335405 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 7.7190. Min Range: -7.7190

Max Act: 7.0513. Min Act: -0.0000

Data Index: 759686 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.7586. Min Act: -0.0000

Data Index: 890730 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.4241. Min Act: -0.0000

Data Index: 426810 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.7084. Min Act: -0.0000

Data Index: 997110 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.5083. Min Act: -0.0000

Data Index: 494499 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.4825. Min Act: -0.0000

Data Index: 405572 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.4607. Min Act: -0.0000

Data Index: 1002257 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.3775. Min Act: -0.0000

Data Index: 928264 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.2585. Min Act: -0.0000

Data Index: 1138495 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.4466. Min Act: -0.0000

Data Index: 1051487 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.1323. Min Act: -0.0000

Data Index: 1311567 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.1132. Min Act: -0.0000

Data Index: 606469 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 7.7190. Min Range: -7.7190

Max Act: 6.0464. Min Act: -0.0000

Data Index: 161569 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 7.7190. Min Range: -7.7190

Max Act: 5.6403. Min Act: -0.0000

Data Index: 205308 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 7.7190. Min Range: -7.7190

Max Act: 5.5581. Min Act: -0.0000

Data Index: 637737 (C4 (Web Text))

Max Activating Token Index: 976