Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4010 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5901. Min Act: -0.0000

Data Index: 946759 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1162200 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5951. Min Act: -0.0000

Data Index: 913134 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5516. Min Act: -0.0001

Data Index: 257064 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5324. Min Act: -0.0000

Data Index: 585009 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5379. Min Act: -0.0000

Data Index: 450045 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5052. Min Act: -0.0000

Data Index: 346405 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1208668 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1019675 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5200. Min Act: -0.0000

Data Index: 110927 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1055985 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4713. Min Act: -0.0000

Data Index: 421070 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4828. Min Act: -0.0000

Data Index: 552298 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4394. Min Act: -0.0000

Data Index: 895156 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4667. Min Act: -0.0000

Data Index: 132343 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4836. Min Act: -0.0000

Data Index: 18719 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1299539 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1265483 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1355689 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4730. Min Act: -0.0000

Data Index: 235527 (C4 (Web Text))

Max Activating Token Index: 620