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

Dataset: The Pile

Neuron 1898 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: 1.8063. Min Range: -1.8063

Max Act: 1.8063. Min Act: -0.0000

Data Index: 1829270 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4193. Min Act: -0.0000

Data Index: 1033484 (The Pile)

Max Activating Token Index: 490

Text #2

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.1096. Min Act: -0.0000

Data Index: 129368 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.1617. Min Act: -0.0000

Data Index: 70692 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.0990. Min Act: -0.0000

Data Index: 1136338 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.9539. Min Act: -0.0000

Data Index: 371747 (The Pile)

Max Activating Token Index: 732

Text #6

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.0200. Min Act: -0.0000

Data Index: 588849 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.9435. Min Act: -0.0001

Data Index: 282653 (The Pile)

Max Activating Token Index: 400

Text #8

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.8094. Min Act: -0.0000

Data Index: 3875 (The Pile)

Max Activating Token Index: 113

Text #9

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.9422. Min Act: -0.0000

Data Index: 119858 (The Pile)

Max Activating Token Index: 577

Text #10

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.9846. Min Act: -0.0000

Data Index: 405602 (The Pile)

Max Activating Token Index: 554

Text #11

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1263051 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.8887. Min Act: -0.0000

Data Index: 114260 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.9357. Min Act: -0.0000

Data Index: 1733117 (The Pile)

Max Activating Token Index: 772

Text #14

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1645076 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.7715. Min Act: -0.0000

Data Index: 993552 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.7603. Min Act: -0.0000

Data Index: 443318 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1768001 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1354968 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 1.8063. Min Range: -1.8063

Max Act: 0.8699. Min Act: -0.0000

Data Index: 288355 (The Pile)

Max Activating Token Index: 426