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

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

Neuron 2797 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: 7.2308. Min Range: -7.2308

Max Act: 7.2308. Min Act: -0.0000

Data Index: 834587 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 7.2308. Min Range: -7.2308

Max Act: 7.0047. Min Act: -0.0001

Data Index: 184395 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 7.2308. Min Range: -7.2308

Max Act: 6.9066. Min Act: -0.0000

Data Index: 1295944 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 7.2308. Min Range: -7.2308

Max Act: 6.7434. Min Act: -0.0000

Data Index: 1349559 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 7.2308. Min Range: -7.2308

Max Act: 6.2975. Min Act: -0.0000

Data Index: 1259709 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 7.2308. Min Range: -7.2308

Max Act: 6.2626. Min Act: -0.0000

Data Index: 1269747 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 7.2308. Min Range: -7.2308

Max Act: 6.2170. Min Act: -0.0000

Data Index: 528484 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 7.2308. Min Range: -7.2308

Max Act: 6.0219. Min Act: -0.0000

Data Index: 966264 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 7.2308. Min Range: -7.2308

Max Act: 6.0353. Min Act: -0.0000

Data Index: 1193435 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 7.2308. Min Range: -7.2308

Max Act: 6.1863. Min Act: -0.0000

Data Index: 82009 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 7.2308. Min Range: -7.2308

Max Act: 5.9643. Min Act: -0.0000

Data Index: 1060649 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 7.2308. Min Range: -7.2308

Max Act: 5.7600. Min Act: -0.0000

Data Index: 1011033 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 7.2308. Min Range: -7.2308

Max Act: 5.9027. Min Act: -0.0000

Data Index: 584406 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 7.2308. Min Range: -7.2308

Max Act: 6.0850. Min Act: -0.0000

Data Index: 869536 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 7.2308. Min Range: -7.2308

Max Act: 5.8600. Min Act: -0.0000

Data Index: 1149429 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 7.2308. Min Range: -7.2308

Max Act: 5.8834. Min Act: -0.0000

Data Index: 552661 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 7.2308. Min Range: -7.2308

Max Act: 6.0040. Min Act: -0.0000

Data Index: 909783 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 7.2308. Min Range: -7.2308

Max Act: 5.6409. Min Act: -0.0000

Data Index: 425891 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 7.2308. Min Range: -7.2308

Max Act: 5.7832. Min Act: -0.0000

Data Index: 1314505 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 7.2308. Min Range: -7.2308

Max Act: 5.7606. Min Act: -0.0000

Data Index: 82993 (C4 (Web Text))

Max Activating Token Index: 486