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

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

Neuron 2517 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: 2.2744. Min Range: -2.2744

Max Act: 2.2744. Min Act: -0.0000

Data Index: 678823 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 2.2744. Min Range: -2.2744

Max Act: 2.2600. Min Act: -0.0000

Data Index: 951953 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 2.2744. Min Range: -2.2744

Max Act: 2.1878. Min Act: -0.0000

Data Index: 963278 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 2.2744. Min Range: -2.2744

Max Act: 2.2326. Min Act: -0.0000

Data Index: 777140 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.9704. Min Act: -0.0000

Data Index: 542531 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.7991. Min Act: -0.0000

Data Index: 718897 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.8820. Min Act: -0.0000

Data Index: 469750 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.9847. Min Act: -0.0000

Data Index: 453840 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.9703. Min Act: -0.0000

Data Index: 677470 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.9236. Min Act: -0.0000

Data Index: 802540 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.9235. Min Act: -0.0000

Data Index: 766313 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.8609. Min Act: -0.0000

Data Index: 607067 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.8599. Min Act: -0.0000

Data Index: 822353 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.7423. Min Act: -0.0000

Data Index: 32850 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.5332. Min Act: -0.0000

Data Index: 772355 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.5591. Min Act: -0.0000

Data Index: 1287315 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.6271. Min Act: -0.0000

Data Index: 757583 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.6153. Min Act: -0.0000

Data Index: 46586 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.4848. Min Act: -0.0000

Data Index: 878564 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 2.2744. Min Range: -2.2744

Max Act: 1.4665. Min Act: -0.0000

Data Index: 437272 (C4 (Web Text))

Max Activating Token Index: 350