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

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

Neuron 962 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: 1.8989. Min Range: -1.8989

Max Act: 1.6920. Min Act: -0.0000

Data Index: 245615 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.8989. Min Act: -0.0000

Data Index: 131228 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.8389. Min Act: -0.0001

Data Index: 1399039 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.7200. Min Act: -0.0000

Data Index: 636694 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.8014. Min Act: -0.0000

Data Index: 1026322 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.6266. Min Act: -0.0000

Data Index: 86949 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.7437. Min Act: -0.0000

Data Index: 1337291 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5750. Min Act: -0.0000

Data Index: 873015 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5977. Min Act: -0.0000

Data Index: 1432683 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.6280. Min Act: -0.0000

Data Index: 265177 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.6256. Min Act: -0.0000

Data Index: 362817 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5481. Min Act: -0.0000

Data Index: 387138 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5589. Min Act: -0.0000

Data Index: 372148 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5878. Min Act: -0.0000

Data Index: 465819 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.6698. Min Act: -0.0000

Data Index: 1358679 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5294. Min Act: -0.0000

Data Index: 185576 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5293. Min Act: -0.0000

Data Index: 371017 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5186. Min Act: -0.0000

Data Index: 643803 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5387. Min Act: -0.0000

Data Index: 249862 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5615. Min Act: -0.0000

Data Index: 477996 (C4 (Web Text))

Max Activating Token Index: 700