Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1118 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5469. Min Range: -2.5469

Max Act: 2.5469. Min Act: -0.0000

Data Index: 359432 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 2.5469. Min Range: -2.5469

Max Act: 2.3372. Min Act: -0.0000

Data Index: 136350 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 2.5469. Min Range: -2.5469

Max Act: 2.3632. Min Act: -0.0000

Data Index: 559536 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 2.5469. Min Range: -2.5469

Max Act: 2.1935. Min Act: -0.0000

Data Index: 825133 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 2.5469. Min Range: -2.5469

Max Act: 2.1910. Min Act: -0.0000

Data Index: 114684 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 2.5469. Min Range: -2.5469

Max Act: 2.0281. Min Act: -0.0000

Data Index: 568608 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.8313. Min Act: -0.0000

Data Index: 887792 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.6919. Min Act: -0.0000

Data Index: 1229770 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.7042. Min Act: -0.0000

Data Index: 663826 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.7094. Min Act: -0.0000

Data Index: 593861 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.8041. Min Act: -0.0000

Data Index: 730209 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.8072. Min Act: -0.0000

Data Index: 603620 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.5619. Min Act: -0.0000

Data Index: 1328652 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.4779. Min Act: -0.0000

Data Index: 741361 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.6377. Min Act: -0.0000

Data Index: 876155 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.6129. Min Act: -0.0000

Data Index: 1181085 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.6103. Min Act: -0.0000

Data Index: 389970 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.5262. Min Act: -0.0000

Data Index: 403055 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.5921. Min Act: -0.0000

Data Index: 98627 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 2.5469. Min Range: -2.5469

Max Act: 1.5188. Min Act: -0.0000

Data Index: 650675 (C4 (Web Text))

Max Activating Token Index: 867