Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3751 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5736. Min Act: -0.0000

Data Index: 818490 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.6305. Min Act: -0.0000

Data Index: 563926 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1049403 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.6032. Min Act: -0.0000

Data Index: 909540 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5863. Min Act: -0.0000

Data Index: 645446 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5865. Min Act: -0.0000

Data Index: 626004 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5662. Min Act: -0.0000

Data Index: 935608 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5903. Min Act: -0.0000

Data Index: 934926 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5590. Min Act: -0.0001

Data Index: 331065 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1069132 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5700. Min Act: -0.0000

Data Index: 476244 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5565. Min Act: -0.0000

Data Index: 146410 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5646. Min Act: -0.0000

Data Index: 13487 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5623. Min Act: -0.0000

Data Index: 931940 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5600. Min Act: -0.0000

Data Index: 938483 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5245. Min Act: -0.0001

Data Index: 774105 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5570. Min Act: -0.0000

Data Index: 480378 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5373. Min Act: -0.0001

Data Index: 141644 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5281. Min Act: -0.0000

Data Index: 724332 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.6305. Min Range: -0.6305

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1150808 (C4 (Web Text))

Max Activating Token Index: 846