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

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

Neuron 1484 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: 0.9125. Min Range: -0.9125

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1221741 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1273818 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.7572. Min Act: -0.0000

Data Index: 272346 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.7838. Min Act: -0.0000

Data Index: 175820 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.7009. Min Act: -0.0000

Data Index: 900959 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.6202. Min Act: -0.0000

Data Index: 2130 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.5753. Min Act: -0.0000

Data Index: 95444 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1317014 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.5545. Min Act: -0.0000

Data Index: 78758 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.5554. Min Act: -0.0000

Data Index: 797231 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.5503. Min Act: -0.0000

Data Index: 656201 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1237090 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.5366. Min Act: -0.0000

Data Index: 773864 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.5113. Min Act: -0.0000

Data Index: 64815 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.5579. Min Act: -0.0000

Data Index: 66430 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.5331. Min Act: -0.0000

Data Index: 559158 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.4967. Min Act: -0.0000

Data Index: 658804 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.4880. Min Act: -0.0000

Data Index: 129646 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.5019. Min Act: -0.0000

Data Index: 93407 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.9125. Min Range: -0.9125

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1286942 (C4 (Web Text))

Max Activating Token Index: 224