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

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

Neuron 5018 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: 6.4217. Min Range: -6.4217

Max Act: 6.4217. Min Act: -0.0000

Data Index: 127745 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.7269. Min Act: -0.0000

Data Index: 1044260 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.3529. Min Act: -0.0000

Data Index: 443840 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.1155. Min Act: -0.0000

Data Index: 597823 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.0631. Min Act: -0.0000

Data Index: 344816 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.7826. Min Act: -0.0000

Data Index: 1220520 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.9691. Min Act: -0.0000

Data Index: 615453 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.0864. Min Act: -0.0000

Data Index: 178800 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.8537. Min Act: -0.0000

Data Index: 874290 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.8529. Min Act: -0.0000

Data Index: 871865 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.6507. Min Act: -0.0000

Data Index: 853615 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.7976. Min Act: -0.0000

Data Index: 829730 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.5543. Min Act: -0.0000

Data Index: 1251687 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.6834. Min Act: -0.0000

Data Index: 185049 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.8654. Min Act: -0.0000

Data Index: 1113720 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.8236. Min Act: -0.0000

Data Index: 56862 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.7993. Min Act: -0.0000

Data Index: 600946 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.4682. Min Act: -0.0000

Data Index: 433785 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.6039. Min Act: -0.0000

Data Index: 485874 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.5622. Min Act: -0.0000

Data Index: 977345 (C4 (Web Text))

Max Activating Token Index: 1002