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

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

Neuron 3126 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.7619. Min Act: -0.0000

Data Index: 1070569 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.5270. Min Act: -0.0000

Data Index: 16942 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.5828. Min Act: -0.0000

Data Index: 540854 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.5429. Min Act: -0.0000

Data Index: 978625 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1064460 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.4879. Min Act: -0.0000

Data Index: 16948 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.4693. Min Act: -0.0000

Data Index: 628081 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.4789. Min Act: -0.0000

Data Index: 1232766 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.4410. Min Act: -0.0000

Data Index: 523790 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.4066. Min Act: -0.0000

Data Index: 940736 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.3045. Min Act: -0.0000

Data Index: 579907 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.3114. Min Act: -0.0000

Data Index: 334117 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.2866. Min Act: -0.0000

Data Index: 731528 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.2715. Min Act: -0.0000

Data Index: 599463 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1041628 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.2637. Min Act: -0.0000

Data Index: 390537 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.2359. Min Act: -0.0000

Data Index: 691619 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1042776 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.1807. Min Act: -0.0000

Data Index: 100962 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.7619. Min Range: -1.7619

Max Act: 1.1252. Min Act: -0.0000

Data Index: 141876 (C4 (Web Text))

Max Activating Token Index: 98