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

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

Neuron 1856 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.7735. Min Act: -0.0000

Data Index: 186381 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.7830. Min Act: -0.0000

Data Index: 433292 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.7662. Min Act: -0.0000

Data Index: 610642 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.7483. Min Act: -0.0000

Data Index: 270857 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1266525 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1454368 (Python Code)

Max Activating Token Index: 1000

Text #6

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6836. Min Act: -0.0000

Data Index: 707268 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6245. Min Act: -0.0000

Data Index: 834293 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6681. Min Act: -0.0000

Data Index: 49625 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6509. Min Act: -0.0000

Data Index: 127718 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6992. Min Act: -0.0000

Data Index: 847591 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1104536 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1070685 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6332. Min Act: -0.0000

Data Index: 238993 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6549. Min Act: -0.0000

Data Index: 725598 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1169123 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1186026 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6109. Min Act: -0.0000

Data Index: 770906 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6063. Min Act: -0.0000

Data Index: 826878 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1057971 (C4 (Web Text))

Max Activating Token Index: 19