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

Dataset: The Pile

Neuron 642 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: 0.9877. Min Range: -0.9877

Max Act: 0.8616. Min Act: -0.0000

Data Index: 864416 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.8503. Min Act: -0.0000

Data Index: 692010 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.8569. Min Act: -0.0000

Data Index: 685088 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.8523. Min Act: -0.0000

Data Index: 958849 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1083539 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1662643 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.5769. Min Act: -0.0000

Data Index: 297538 (The Pile)

Max Activating Token Index: 825

Text #7

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1665359 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1070685 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6158. Min Act: -0.0000

Data Index: 454785 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1743347 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1602231 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1158063 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1459823 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1313098 (The Pile)

Max Activating Token Index: 590

Text #15

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.5722. Min Act: -0.0000

Data Index: 280511 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.5879. Min Act: -0.0000

Data Index: 175576 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1463176 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.5813. Min Act: -0.0000

Data Index: 888028 (The Pile)

Max Activating Token Index: 734

Text #19

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.5582. Min Act: -0.0000

Data Index: 254047 (The Pile)

Max Activating Token Index: 778