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

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

Neuron 3379 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.4505. Min Act: -0.0000

Data Index: 201923 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5116. Min Act: -0.0000

Data Index: 674007 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5899. Min Act: -0.0000

Data Index: 512623 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5641. Min Act: -0.0000

Data Index: 1094547 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.4018. Min Act: -0.0000

Data Index: 1263906 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.4611. Min Act: -0.0000

Data Index: 177229 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1181531 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.3207. Min Act: -0.0000

Data Index: 1321010 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.2860. Min Act: -0.0000

Data Index: 817847 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.2374. Min Act: -0.0000

Data Index: 786397 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.2718. Min Act: -0.0000

Data Index: 69124 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1577. Min Act: -0.0000

Data Index: 863776 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1131708 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1854. Min Act: -0.0000

Data Index: 759579 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.0724. Min Act: -0.0000

Data Index: 244233 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1260. Min Act: -0.0000

Data Index: 1316128 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1618. Min Act: -0.0000

Data Index: 936188 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1530. Min Act: -0.0000

Data Index: 163839 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1013. Min Act: -0.0000

Data Index: 343484 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.0889. Min Act: -0.0000

Data Index: 1214589 (C4 (Web Text))

Max Activating Token Index: 37