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

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

Neuron 2351 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1114187 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5283. Min Act: -0.0000

Data Index: 328463 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1056670 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4928. Min Act: -0.0000

Data Index: 860410 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4933. Min Act: -0.0000

Data Index: 112721 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5184. Min Act: 0.0000

Data Index: 751405 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4752. Min Act: -0.0000

Data Index: 923393 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4722. Min Act: 0.0001

Data Index: 165966 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4874. Min Act: 0.0000

Data Index: 684288 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4801. Min Act: 0.0000

Data Index: 584752 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1099468 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1338236 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4689. Min Act: -0.0000

Data Index: 276530 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4677. Min Act: -0.0000

Data Index: 714214 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4405. Min Act: -0.0000

Data Index: 605890 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4528. Min Act: -0.0000

Data Index: 154962 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4696. Min Act: 0.0001

Data Index: 109237 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1057812 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4582. Min Act: -0.0000

Data Index: 393204 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1079019 (C4 (Web Text))

Max Activating Token Index: 306