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

Dataset: The Pile

Neuron 1587 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: 1.8474. Min Range: -1.8474

Max Act: 1.8474. Min Act: -0.0000

Data Index: 922247 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.7146. Min Act: -0.0000

Data Index: 1859331 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.5840. Min Act: -0.0000

Data Index: 1114489 (The Pile)

Max Activating Token Index: 250

Text #3

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4157. Min Act: -0.0000

Data Index: 1521341 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.3922. Min Act: -0.0000

Data Index: 520273 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1603845 (The Pile)

Max Activating Token Index: 771

Text #6

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4058. Min Act: -0.0000

Data Index: 655756 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1645859 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.2797. Min Act: -0.0000

Data Index: 472536 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1945135 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.2699. Min Act: -0.0000

Data Index: 1942797 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.2930. Min Act: -0.0000

Data Index: 616057 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1908598 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.2471. Min Act: -0.0000

Data Index: 76341 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.2033. Min Act: -0.0000

Data Index: 600652 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.1877. Min Act: -0.0000

Data Index: 139555 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.1970. Min Act: -0.0000

Data Index: 112575 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.2385. Min Act: -0.0000

Data Index: 1874711 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1422417 (The Pile)

Max Activating Token Index: 50

Text #19

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.1478. Min Act: -0.0000

Data Index: 38348 (The Pile)

Max Activating Token Index: 174