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

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

Neuron 3040 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.6749. Min Act: -0.0000

Data Index: 670262 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1269849 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.6475. Min Act: -0.0000

Data Index: 546907 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.6414. Min Act: -0.0000

Data Index: 820777 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.6273. Min Act: -0.0000

Data Index: 550997 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.6058. Min Act: -0.0000

Data Index: 983686 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5833. Min Act: -0.0000

Data Index: 798312 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1194988 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5265. Min Act: -0.0000

Data Index: 684201 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5276. Min Act: 0.0000

Data Index: 646163 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5627. Min Act: -0.0000

Data Index: 670521 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1184540 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5339. Min Act: -0.0000

Data Index: 834426 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1210078 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1048811 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1162185 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4638. Min Act: -0.0000

Data Index: 472523 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1133563 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4781. Min Act: -0.0000

Data Index: 253947 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4928. Min Act: -0.0000

Data Index: 421975 (C4 (Web Text))

Max Activating Token Index: 825