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

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

Neuron 755 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8811. Min Range: -6.8811

Max Act: 6.8077. Min Act: -0.0000

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 6.8811. Min Range: -6.8811

Max Act: 6.0305. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 6.8811. Min Range: -6.8811

Max Act: 6.8811. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 6.8811. Min Range: -6.8811

Max Act: 6.4458. Min Act: -0.0000

Data Index: 369720 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 6.8811. Min Range: -6.8811

Max Act: 6.1678. Min Act: -0.0000

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 6.8811. Min Range: -6.8811

Max Act: 5.3063. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 6.8811. Min Range: -6.8811

Max Act: 5.0835. Min Act: -0.0000

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 6.8811. Min Range: -6.8811

Max Act: 4.7364. Min Act: -0.0000

Data Index: 1449966 (Python Code)

Max Activating Token Index: 756

Text #8

Max Range: 6.8811. Min Range: -6.8811

Max Act: 4.7228. Min Act: -0.0000

Data Index: 1487410 (Python Code)

Max Activating Token Index: 277

Text #9

Max Range: 6.8811. Min Range: -6.8811

Max Act: 4.2875. Min Act: -0.0000

Data Index: 1368064 (Python Code)

Max Activating Token Index: 298

Text #10

Max Range: 6.8811. Min Range: -6.8811

Max Act: 4.2283. Min Act: -0.0000

Data Index: 1439366 (Python Code)

Max Activating Token Index: 636

Text #11

Max Range: 6.8811. Min Range: -6.8811

Max Act: 3.9868. Min Act: -0.0000

Data Index: 1605799 (Python Code)

Max Activating Token Index: 1020

Text #12

Max Range: 6.8811. Min Range: -6.8811

Max Act: 4.1428. Min Act: -0.0000

Data Index: 1576739 (Python Code)

Max Activating Token Index: 757

Text #13

Max Range: 6.8811. Min Range: -6.8811

Max Act: 3.8310. Min Act: -0.0000

Data Index: 1489791 (Python Code)

Max Activating Token Index: 268

Text #14

Max Range: 6.8811. Min Range: -6.8811

Max Act: 3.9121. Min Act: -0.0000

Data Index: 1090088 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 6.8811. Min Range: -6.8811

Max Act: 3.7712. Min Act: -0.0000

Data Index: 246176 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 6.8811. Min Range: -6.8811

Max Act: 3.5954. Min Act: -0.0000

Data Index: 452177 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 6.8811. Min Range: -6.8811

Max Act: 3.8828. Min Act: -0.0000

Data Index: 1071085 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 6.8811. Min Range: -6.8811

Max Act: 3.9487. Min Act: -0.0000

Data Index: 161524 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 6.8811. Min Range: -6.8811

Max Act: 3.3888. Min Act: -0.0000

Data Index: 797284 (C4 (Web Text))

Max Activating Token Index: 1003