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

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

Neuron 3987 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9753. Min Act: -0.0000

Data Index: 159015 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9881. Min Act: -0.0000

Data Index: 971473 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9837. Min Act: -0.0000

Data Index: 398723 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9852. Min Act: -0.0000

Data Index: 707217 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9216. Min Act: -0.0000

Data Index: 872030 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1348496 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8618. Min Act: -0.0000

Data Index: 453066 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1060321 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1063295 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8736. Min Act: -0.0000

Data Index: 354370 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7751. Min Act: -0.0000

Data Index: 83481 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1236683 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7412. Min Act: -0.0000

Data Index: 479609 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1213208 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7303. Min Act: -0.0000

Data Index: 894215 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7022. Min Act: -0.0000

Data Index: 724270 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7068. Min Act: -0.0000

Data Index: 514532 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7114. Min Act: -0.0000

Data Index: 799551 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6859. Min Act: -0.0000

Data Index: 316938 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6857. Min Act: -0.0000

Data Index: 351285 (C4 (Web Text))

Max Activating Token Index: 357