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

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

Neuron 4760 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: 0.6097. Min Range: -0.6097

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1206853 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1171409 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5461. Min Act: -0.0000

Data Index: 280167 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5572. Min Act: -0.0000

Data Index: 277963 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5425. Min Act: -0.0000

Data Index: 838923 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1011657 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.4867. Min Act: -0.0000

Data Index: 1086091 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.4395. Min Act: -0.0000

Data Index: 973996 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.4961. Min Act: -0.0000

Data Index: 666976 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.4765. Min Act: -0.0000

Data Index: 925639 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.4501. Min Act: -0.0000

Data Index: 907845 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.4351. Min Act: -0.0000

Data Index: 613393 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.3595. Min Act: -0.0000

Data Index: 629238 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1015904 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.3863. Min Act: -0.0000

Data Index: 932472 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.3874. Min Act: -0.0000

Data Index: 984503 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.4010. Min Act: -0.0000

Data Index: 310774 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.3854. Min Act: -0.0000

Data Index: 333325 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1228113 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1074711 (C4 (Web Text))

Max Activating Token Index: 490