Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1978 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1092290 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2331. Min Act: -0.0002

Data Index: 1279070 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2296. Min Act: -0.0001

Data Index: 619704 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2062. Min Act: -0.0001

Data Index: 863169 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1943. Min Act: -0.0001

Data Index: 1150659 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2040. Min Act: -0.0002

Data Index: 385661 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2059. Min Act: -0.0001

Data Index: 1114612 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2082. Min Act: -0.0001

Data Index: 617785 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1887. Min Act: -0.0001

Data Index: 1146985 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2012. Min Act: -0.0002

Data Index: 889007 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1976. Min Act: -0.0002

Data Index: 473126 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1919. Min Act: -0.0001

Data Index: 207994 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1983. Min Act: -0.0001

Data Index: 475536 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2010. Min Act: -0.0001

Data Index: 33772 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2028. Min Act: -0.0002

Data Index: 890643 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2170. Min Act: -0.0001

Data Index: 194001 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2173. Min Act: -0.0002

Data Index: 1105031 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2083. Min Act: -0.0001

Data Index: 996607 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1948. Min Act: -0.0001

Data Index: 823666 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1889. Min Act: -0.0002

Data Index: 1077624 (C4 (Web Text))

Max Activating Token Index: 800