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

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

Neuron 5082 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: 0.5817. Min Range: -0.5817

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1332463 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5817. Min Act: -0.0000

Data Index: 97184 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5563. Min Act: -0.0000

Data Index: 936350 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5077. Min Act: -0.0000

Data Index: 766496 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5272. Min Act: -0.0000

Data Index: 633797 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5046. Min Act: -0.0000

Data Index: 314541 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1330759 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1584783 (Python Code)

Max Activating Token Index: 400

Text #8

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5425. Min Act: -0.0000

Data Index: 906932 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5250. Min Act: -0.0000

Data Index: 961499 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5136. Min Act: -0.0000

Data Index: 961276 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4765. Min Act: -0.0000

Data Index: 686568 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5026. Min Act: -0.0000

Data Index: 664198 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4941. Min Act: -0.0000

Data Index: 637489 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4710. Min Act: -0.0000

Data Index: 578797 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1193067 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1561966 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4368. Min Act: -0.0000

Data Index: 55904 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4527. Min Act: -0.0000

Data Index: 56072 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4464. Min Act: -0.0000

Data Index: 334124 (C4 (Web Text))

Max Activating Token Index: 200