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

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

Neuron 4555 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1289265 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1088342 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0838. Min Act: -0.0000

Data Index: 328295 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1298491 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0775. Min Act: -0.0001

Data Index: 456788 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0730. Min Act: -0.0000

Data Index: 749602 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0719. Min Act: -0.0000

Data Index: 995022 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1008731 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0705. Min Act: -0.0000

Data Index: 600832 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0720. Min Act: -0.0000

Data Index: 844488 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0702. Min Act: -0.0000

Data Index: 786041 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0693. Min Act: -0.0000

Data Index: 1293383 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0680. Min Act: -0.0000

Data Index: 289072 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1246576 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0680. Min Act: -0.0000

Data Index: 160906 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0699. Min Act: -0.0000

Data Index: 139410 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1294464 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1093893 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0665. Min Act: -0.0001

Data Index: 976200 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0686. Min Act: -0.0000

Data Index: 872300 (C4 (Web Text))

Max Activating Token Index: 953