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

Dataset: The Pile

Neuron 1288 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: 1.8611. Min Range: -1.8611

Max Act: 1.7532. Min Act: -0.0000

Data Index: 1769692 (The Pile)

Max Activating Token Index: 942

Text #1

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.8611. Min Act: -0.0000

Data Index: 814110 (The Pile)

Max Activating Token Index: 549

Text #2

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.6819. Min Act: -0.0000

Data Index: 628489 (The Pile)

Max Activating Token Index: 276

Text #3

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.5158. Min Act: -0.0000

Data Index: 1150971 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.4223. Min Act: -0.0000

Data Index: 501244 (The Pile)

Max Activating Token Index: 221

Text #5

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3905. Min Act: -0.0000

Data Index: 650127 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1494036 (The Pile)

Max Activating Token Index: 849

Text #7

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.2550. Min Act: -0.0000

Data Index: 660334 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.4714. Min Act: -0.0000

Data Index: 1553665 (The Pile)

Max Activating Token Index: 506

Text #9

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1479363 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.1812. Min Act: -0.0000

Data Index: 645620 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3104. Min Act: -0.0000

Data Index: 802819 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.2931. Min Act: -0.0000

Data Index: 741808 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1322596 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.1313. Min Act: -0.0000

Data Index: 54017 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3284. Min Act: -0.0000

Data Index: 1109659 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.2471. Min Act: -0.0000

Data Index: 729771 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.2290. Min Act: -0.0000

Data Index: 496781 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1488850 (The Pile)

Max Activating Token Index: 32

Text #19

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1156578 (The Pile)

Max Activating Token Index: 1021