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

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

Neuron 5071 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: 7.0838. Min Range: -7.0838

Max Act: 7.0838. Min Act: -0.0000

Data Index: 109907 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 7.0838. Min Range: -7.0838

Max Act: 6.8734. Min Act: -0.0000

Data Index: 363193 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 7.0838. Min Range: -7.0838

Max Act: 6.5080. Min Act: -0.0000

Data Index: 634341 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 7.0838. Min Range: -7.0838

Max Act: 6.2648. Min Act: -0.0000

Data Index: 277111 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 7.0838. Min Range: -7.0838

Max Act: 6.3055. Min Act: -0.0000

Data Index: 639491 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 7.0838. Min Range: -7.0838

Max Act: 6.6350. Min Act: -0.0000

Data Index: 192359 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 7.0838. Min Range: -7.0838

Max Act: 6.1223. Min Act: -0.0000

Data Index: 341065 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 7.0838. Min Range: -7.0838

Max Act: 6.6891. Min Act: -0.0000

Data Index: 1192501 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 7.0838. Min Range: -7.0838

Max Act: 6.0412. Min Act: -0.0000

Data Index: 1113771 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 7.0838. Min Range: -7.0838

Max Act: 5.7774. Min Act: -0.0000

Data Index: 85148 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 7.0838. Min Range: -7.0838

Max Act: 5.8803. Min Act: -0.0000

Data Index: 12535 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 7.0838. Min Range: -7.0838

Max Act: 6.0470. Min Act: -0.0000

Data Index: 1150848 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 7.0838. Min Range: -7.0838

Max Act: 5.9222. Min Act: -0.0000

Data Index: 319574 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 7.0838. Min Range: -7.0838

Max Act: 5.5382. Min Act: -0.0000

Data Index: 401923 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 7.0838. Min Range: -7.0838

Max Act: 5.9025. Min Act: -0.0000

Data Index: 1002477 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 7.0838. Min Range: -7.0838

Max Act: 5.6408. Min Act: -0.0000

Data Index: 333555 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 7.0838. Min Range: -7.0838

Max Act: 5.6282. Min Act: -0.0000

Data Index: 220066 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 7.0838. Min Range: -7.0838

Max Act: 5.6344. Min Act: -0.0000

Data Index: 734205 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 7.0838. Min Range: -7.0838

Max Act: 5.7797. Min Act: -0.0000

Data Index: 472813 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 7.0838. Min Range: -7.0838

Max Act: 5.3457. Min Act: -0.0000

Data Index: 547058 (C4 (Web Text))

Max Activating Token Index: 91