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

Dataset: The Pile

Neuron 4075 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1666876 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6868. Min Act: -0.0000

Data Index: 307074 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5595. Min Act: -0.0000

Data Index: 493843 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1389108 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5691. Min Act: -0.0000

Data Index: 222227 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5370. Min Act: -0.0000

Data Index: 573442 (The Pile)

Max Activating Token Index: 95

Text #6

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5367. Min Act: -0.0000

Data Index: 372185 (The Pile)

Max Activating Token Index: 905

Text #7

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5458. Min Act: -0.0000

Data Index: 667874 (The Pile)

Max Activating Token Index: 78

Text #8

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5446. Min Act: -0.0000

Data Index: 55340 (The Pile)

Max Activating Token Index: 1014

Text #9

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1860866 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1798970 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5356. Min Act: -0.0000

Data Index: 238586 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1683695 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5320. Min Act: -0.0000

Data Index: 70678 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5022. Min Act: -0.0000

Data Index: 395094 (The Pile)

Max Activating Token Index: 804

Text #15

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5094. Min Act: -0.0000

Data Index: 284541 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.4929. Min Act: -0.0000

Data Index: 314316 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1788777 (The Pile)

Max Activating Token Index: 29

Text #18

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1386287 (The Pile)

Max Activating Token Index: 778

Text #19

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1918856 (The Pile)

Max Activating Token Index: 828