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

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

Neuron 2690 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2661. Min Range: -2.2661

Max Act: 2.2661. Min Act: -0.0000

Data Index: 460379 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 2.2661. Min Range: -2.2661

Max Act: 2.0104. Min Act: -0.0000

Data Index: 87282 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 2.2661. Min Range: -2.2661

Max Act: 2.1546. Min Act: -0.0000

Data Index: 1262800 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.8446. Min Act: -0.0000

Data Index: 420791 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 2.2661. Min Range: -2.2661

Max Act: 2.0229. Min Act: -0.0000

Data Index: 564581 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.8694. Min Act: -0.0000

Data Index: 600855 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.9503. Min Act: -0.0000

Data Index: 435367 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.9345. Min Act: -0.0000

Data Index: 980675 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.7962. Min Act: -0.0000

Data Index: 1207490 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.8381. Min Act: -0.0000

Data Index: 828960 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.8701. Min Act: -0.0000

Data Index: 403028 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.8903. Min Act: -0.0000

Data Index: 712147 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.7282. Min Act: -0.0000

Data Index: 140905 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.7892. Min Act: -0.0000

Data Index: 169566 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.5203. Min Act: -0.0000

Data Index: 440796 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.7941. Min Act: -0.0000

Data Index: 1099400 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.5304. Min Act: -0.0000

Data Index: 511627 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.7212. Min Act: -0.0000

Data Index: 50396 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.7536. Min Act: -0.0000

Data Index: 146447 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 2.2661. Min Range: -2.2661

Max Act: 1.6729. Min Act: -0.0000

Data Index: 931980 (C4 (Web Text))

Max Activating Token Index: 807