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

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

Neuron 1693 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6813. Min Act: -0.0000

Data Index: 334464 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6927. Min Act: -0.0000

Data Index: 928920 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6393. Min Act: -0.0000

Data Index: 735883 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6330. Min Act: -0.0000

Data Index: 130414 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1221987 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6109. Min Act: -0.0000

Data Index: 57859 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1018164 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1265579 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6471. Min Act: -0.0000

Data Index: 287526 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6478. Min Act: -0.0000

Data Index: 211584 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1178942 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6040. Min Act: -0.0000

Data Index: 987049 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1291540 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1290867 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1100271 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1116928 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1207608 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6213. Min Act: -0.0000

Data Index: 136976 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6010. Min Act: -0.0000

Data Index: 516557 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5800. Min Act: -0.0000

Data Index: 789494 (C4 (Web Text))

Max Activating Token Index: 336