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

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

Neuron 4065 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0914. Min Range: -2.0914

Max Act: 2.0914. Min Act: -0.0000

Data Index: 1060075 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.9673. Min Act: -0.0000

Data Index: 895329 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.6607. Min Act: -0.0000

Data Index: 267858 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.5565. Min Act: -0.0000

Data Index: 589254 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.5389. Min Act: -0.0000

Data Index: 1230436 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.4209. Min Act: -0.0000

Data Index: 347827 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.4365. Min Act: -0.0000

Data Index: 355425 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.3789. Min Act: -0.0000

Data Index: 315747 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.3578. Min Act: -0.0000

Data Index: 1147691 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.4602. Min Act: -0.0000

Data Index: 460554 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.4285. Min Act: -0.0000

Data Index: 900128 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.3768. Min Act: -0.0000

Data Index: 559527 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.4025. Min Act: -0.0000

Data Index: 1216935 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.3496. Min Act: -0.0000

Data Index: 223409 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.3225. Min Act: -0.0000

Data Index: 488561 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.3754. Min Act: -0.0000

Data Index: 759864 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1204714 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.3009. Min Act: -0.0000

Data Index: 297277 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.2386. Min Act: -0.0000

Data Index: 927589 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 2.0914. Min Range: -2.0914

Max Act: 1.2700. Min Act: -0.0000

Data Index: 1077347 (C4 (Web Text))

Max Activating Token Index: 590