Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 14 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0024. Min Act: -0.0004

Data Index: 355840 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0024. Min Act: -0.0004

Data Index: 507364 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0024. Min Act: -0.0004

Data Index: 50045 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0004

Data Index: 560150 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0025. Min Act: -0.0004

Data Index: 1355852 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0027. Min Act: -0.0004

Data Index: 415427 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0024. Min Act: -0.0004

Data Index: 1307974 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0028. Min Act: -0.0004

Data Index: 791309 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0023. Min Act: -0.0004

Data Index: 306265 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0004

Data Index: 1279177 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0023. Min Act: -0.0004

Data Index: 1291730 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0021. Min Act: -0.0004

Data Index: 290427 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0004

Data Index: 591345 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0004

Data Index: 675044 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0019. Min Act: -0.0004

Data Index: 1316514 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0004

Data Index: 166212 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0020. Min Act: -0.0004

Data Index: 619181 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0023. Min Act: -0.0004

Data Index: 916886 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0004

Data Index: 112005 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0004

Data Index: 1333466 (C4 (Web Text))

Max Activating Token Index: 150