Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 92 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 8.9222. Min Range: -8.9222

Max Act: 8.9222. Min Act: -0.0000

Data Index: 472951 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 8.9222. Min Range: -8.9222

Max Act: 7.2712. Min Act: -0.0000

Data Index: 920327 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 8.9222. Min Range: -8.9222

Max Act: 7.4133. Min Act: -0.0000

Data Index: 353647 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 8.9222. Min Range: -8.9222

Max Act: 7.0300. Min Act: -0.0000

Data Index: 711479 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 8.9222. Min Range: -8.9222

Max Act: 7.1815. Min Act: -0.0000

Data Index: 516795 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 8.9222. Min Range: -8.9222

Max Act: 7.0721. Min Act: -0.0000

Data Index: 244949 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 8.9222. Min Range: -8.9222

Max Act: 7.0966. Min Act: -0.0000

Data Index: 136715 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.8600. Min Act: -0.0000

Data Index: 483558 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.8461. Min Act: -0.0000

Data Index: 782222 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 8.9222. Min Range: -8.9222

Max Act: 7.0352. Min Act: -0.0000

Data Index: 1307629 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.6544. Min Act: -0.0000

Data Index: 760106 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.8347. Min Act: -0.0000

Data Index: 63726 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.2147. Min Act: -0.0000

Data Index: 1186311 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.7561. Min Act: -0.0000

Data Index: 1009593 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.5475. Min Act: -0.0000

Data Index: 501578 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.5352. Min Act: -0.0000

Data Index: 493208 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.6634. Min Act: -0.0000

Data Index: 564795 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.8298. Min Act: -0.0000

Data Index: 741737 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.6032. Min Act: -0.0000

Data Index: 470875 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 8.9222. Min Range: -8.9222

Max Act: 6.3389. Min Act: -0.0000

Data Index: 132533 (C4 (Web Text))

Max Activating Token Index: 850