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

Dataset: The Pile

Neuron 1225 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: 0.9567. Min Range: -0.9567

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1345184 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8820. Min Act: -0.0000

Data Index: 682572 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8020. Min Act: -0.0000

Data Index: 976843 (The Pile)

Max Activating Token Index: 148

Text #3

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7657. Min Act: -0.0000

Data Index: 1552405 (The Pile)

Max Activating Token Index: 390

Text #4

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1017243 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1335137 (The Pile)

Max Activating Token Index: 354

Text #6

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7769. Min Act: -0.0000

Data Index: 248778 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7620. Min Act: -0.0000

Data Index: 900863 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1781128 (The Pile)

Max Activating Token Index: 117

Text #9

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1895690 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1260839 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7273. Min Act: -0.0000

Data Index: 632722 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1997407 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6406. Min Act: -0.0000

Data Index: 866795 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1471375 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1123310 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1409376 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1048659 (The Pile)

Max Activating Token Index: 797

Text #18

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6612. Min Act: -0.0000

Data Index: 940714 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1490862 (The Pile)

Max Activating Token Index: 444