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

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

Neuron 4454 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: 0.7111. Min Range: -0.7111

Max Act: 0.7111. Min Act: -0.0000

Data Index: 834707 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6391. Min Act: -0.0000

Data Index: 919101 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6369. Min Act: -0.0000

Data Index: 233346 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6703. Min Act: -0.0000

Data Index: 943445 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1071300 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6037. Min Act: -0.0000

Data Index: 689137 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1338655 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6121. Min Act: -0.0000

Data Index: 503292 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5826. Min Act: -0.0000

Data Index: 341568 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5553. Min Act: -0.0000

Data Index: 849878 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5999. Min Act: -0.0000

Data Index: 810556 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1099374 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1320794 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5500. Min Act: -0.0000

Data Index: 161106 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5504. Min Act: -0.0000

Data Index: 990534 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1022799 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1028805 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5376. Min Act: -0.0000

Data Index: 162950 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5548. Min Act: -0.0000

Data Index: 446589 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5511. Min Act: -0.0000

Data Index: 166061 (C4 (Web Text))

Max Activating Token Index: 507