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

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

Neuron 3292 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0734. Min Range: -3.0734

Max Act: 3.0734. Min Act: -0.0000

Data Index: 751930 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.9435. Min Act: -0.0000

Data Index: 34193 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.9229. Min Act: -0.0000

Data Index: 722618 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8193. Min Act: -0.0000

Data Index: 327451 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.9475. Min Act: -0.0000

Data Index: 1100872 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.6121. Min Act: -0.0000

Data Index: 983147 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.6125. Min Act: -0.0000

Data Index: 55795 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.5981. Min Act: -0.0000

Data Index: 216406 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.4292. Min Act: -0.0000

Data Index: 550840 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.4178. Min Act: -0.0000

Data Index: 618956 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.6271. Min Act: -0.0000

Data Index: 505397 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.6230. Min Act: -0.0000

Data Index: 350208 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.4938. Min Act: -0.0000

Data Index: 1067988 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.2422. Min Act: -0.0000

Data Index: 717929 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.3266. Min Act: -0.0000

Data Index: 457537 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.3194. Min Act: -0.0000

Data Index: 622885 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.1412. Min Act: -0.0000

Data Index: 850522 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.2852. Min Act: -0.0000

Data Index: 179161 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.2806. Min Act: -0.0000

Data Index: 596108 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.2288. Min Act: -0.0000

Data Index: 1036539 (C4 (Web Text))

Max Activating Token Index: 259