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

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

Neuron 1688 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.5919. Min Act: -0.0000

Data Index: 1394513 (Python Code)

Max Activating Token Index: 162

Text #1

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1147. Min Act: -0.0000

Data Index: 452388 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1114617 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.0494. Min Act: -0.0000

Data Index: 1121145 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1062. Min Act: -0.0000

Data Index: 583170 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1243327 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.0097. Min Act: -0.0000

Data Index: 1196725 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.9313. Min Act: -0.0000

Data Index: 824418 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.9567. Min Act: -0.0000

Data Index: 233980 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1166309 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.8723. Min Act: -0.0000

Data Index: 416905 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.9031. Min Act: -0.0000

Data Index: 313641 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.8730. Min Act: -0.0000

Data Index: 808818 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.8681. Min Act: -0.0000

Data Index: 1368543 (Python Code)

Max Activating Token Index: 951

Text #14

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1333167 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1406866 (Python Code)

Max Activating Token Index: 895

Text #16

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1547803 (Python Code)

Max Activating Token Index: 627

Text #17

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.9012. Min Act: -0.0000

Data Index: 972797 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.8705. Min Act: -0.0000

Data Index: 1309916 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.9124. Min Act: -0.0000

Data Index: 419851 (C4 (Web Text))

Max Activating Token Index: 902