Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3408 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.4867. Min Act: -0.0000

Data Index: 1098284 (The Pile)

Max Activating Token Index: 672

Text #1

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.2229. Min Act: -0.0000

Data Index: 1574036 (The Pile)

Max Activating Token Index: 94

Text #2

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.0763. Min Act: -0.0000

Data Index: 790169 (The Pile)

Max Activating Token Index: 761

Text #3

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.2005. Min Act: -0.0000

Data Index: 687188 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.1208. Min Act: -0.0000

Data Index: 1630770 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1023123 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.1763. Min Act: -0.0000

Data Index: 559592 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1194535 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 1.4867. Min Range: -1.4867

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1700708 (The Pile)

Max Activating Token Index: 180

Text #9

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.1096. Min Act: -0.0000

Data Index: 930872 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.0086. Min Act: -0.0000

Data Index: 231201 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 1.4867. Min Range: -1.4867

Max Act: 0.9536. Min Act: -0.0000

Data Index: 870340 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.0031. Min Act: -0.0000

Data Index: 1424142 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 1.4867. Min Range: -1.4867

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1318285 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 1.4867. Min Range: -1.4867

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1757443 (The Pile)

Max Activating Token Index: 516

Text #15

Max Range: 1.4867. Min Range: -1.4867

Max Act: 0.9088. Min Act: -0.0000

Data Index: 805014 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 1.4867. Min Range: -1.4867

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1237947 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 1.4867. Min Range: -1.4867

Max Act: 1.0127. Min Act: -0.0000

Data Index: 297869 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 1.4867. Min Range: -1.4867

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1964249 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 1.4867. Min Range: -1.4867

Max Act: 0.9675. Min Act: -0.0000

Data Index: 198771 (The Pile)

Max Activating Token Index: 211