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

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

Neuron 2072 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1759. Min Range: -4.1759

Max Act: 4.1759. Min Act: -0.0000

Data Index: 976570 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 4.1759. Min Range: -4.1759

Max Act: 2.4622. Min Act: -0.0000

Data Index: 501523 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 4.1759. Min Range: -4.1759

Max Act: 2.2187. Min Act: -0.0000

Data Index: 666886 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 4.1759. Min Range: -4.1759

Max Act: 2.1857. Min Act: -0.0000

Data Index: 374393 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 4.1759. Min Range: -4.1759

Max Act: 2.1894. Min Act: -0.0000

Data Index: 542642 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 4.1759. Min Range: -4.1759

Max Act: 2.1672. Min Act: -0.0000

Data Index: 60836 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 4.1759. Min Range: -4.1759

Max Act: 2.2231. Min Act: -0.0000

Data Index: 752986 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 4.1759. Min Range: -4.1759

Max Act: 1.9934. Min Act: -0.0000

Data Index: 550832 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 4.1759. Min Range: -4.1759

Max Act: 2.0100. Min Act: -0.0000

Data Index: 504747 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 4.1759. Min Range: -4.1759

Max Act: 2.0776. Min Act: -0.0000

Data Index: 1249778 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 4.1759. Min Range: -4.1759

Max Act: 1.8467. Min Act: -0.0000

Data Index: 900855 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 4.1759. Min Range: -4.1759

Max Act: 1.9339. Min Act: -0.0000

Data Index: 1068549 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 4.1759. Min Range: -4.1759

Max Act: 1.8135. Min Act: -0.0000

Data Index: 620736 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 4.1759. Min Range: -4.1759

Max Act: 1.9068. Min Act: -0.0000

Data Index: 280723 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 4.1759. Min Range: -4.1759

Max Act: 1.9056. Min Act: -0.0000

Data Index: 192833 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 4.1759. Min Range: -4.1759

Max Act: 1.7756. Min Act: -0.0000

Data Index: 710715 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 4.1759. Min Range: -4.1759

Max Act: 1.7698. Min Act: -0.0001

Data Index: 736016 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 4.1759. Min Range: -4.1759

Max Act: 1.7029. Min Act: -0.0000

Data Index: 287498 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 4.1759. Min Range: -4.1759

Max Act: 1.6978. Min Act: -0.0000

Data Index: 639211 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 4.1759. Min Range: -4.1759

Max Act: 1.6502. Min Act: -0.0000

Data Index: 833894 (C4 (Web Text))

Max Activating Token Index: 484