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

Dataset: The Pile

Neuron 886 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.5859. Min Act: -0.0000

Data Index: 936672 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1696667 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.5173. Min Act: -0.0000

Data Index: 875429 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1206663 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1196840 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1520144 (The Pile)

Max Activating Token Index: 495

Text #6

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1991334 (The Pile)

Max Activating Token Index: 365

Text #7

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1159023 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1183088 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1538376 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1913636 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.3596. Min Act: -0.0000

Data Index: 489511 (The Pile)

Max Activating Token Index: 763

Text #12

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4023. Min Act: -0.0000

Data Index: 273917 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1076041 (The Pile)

Max Activating Token Index: 95

Text #14

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1179053 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1707678 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4023. Min Act: -0.0000

Data Index: 217785 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1002023 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1904405 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.3766. Min Act: -0.0000

Data Index: 778016 (The Pile)

Max Activating Token Index: 985