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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4822 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5785. Min Range: -2.5785

Max Act: 2.5785. Min Act: -0.0000

Data Index: 973214 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 2.5785. Min Range: -2.5785

Max Act: 2.2002. Min Act: -0.0000

Data Index: 1288808 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 2.5785. Min Range: -2.5785

Max Act: 2.1649. Min Act: -0.0000

Data Index: 814929 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 2.5785. Min Range: -2.5785

Max Act: 2.0794. Min Act: -0.0000

Data Index: 912978 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.9186. Min Act: -0.0000

Data Index: 129298 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 2.5785. Min Range: -2.5785

Max Act: 2.0297. Min Act: -0.0000

Data Index: 1307516 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 2.5785. Min Range: -2.5785

Max Act: 2.0041. Min Act: -0.0000

Data Index: 1033129 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.9798. Min Act: -0.0000

Data Index: 131931 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.9644. Min Act: -0.0000

Data Index: 256919 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.9458. Min Act: -0.0000

Data Index: 816716 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 2.5785. Min Range: -2.5785

Max Act: 2.0123. Min Act: -0.0000

Data Index: 1042159 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.7351. Min Act: -0.0000

Data Index: 1031358 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 2.5785. Min Range: -2.5785

Max Act: 2.0271. Min Act: -0.0000

Data Index: 767449 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.9105. Min Act: -0.0000

Data Index: 718521 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.8166. Min Act: -0.0000

Data Index: 208940 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.9217. Min Act: -0.0000

Data Index: 299635 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.8817. Min Act: -0.0000

Data Index: 439999 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.7834. Min Act: -0.0000

Data Index: 102073 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.7743. Min Act: -0.0000

Data Index: 1229786 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 2.5785. Min Range: -2.5785

Max Act: 1.7435. Min Act: -0.0000

Data Index: 1108790 (C4 (Web Text))

Max Activating Token Index: 435