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

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

Neuron 1937 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: 4.0819. Min Range: -4.0819

Max Act: 4.0819. Min Act: -0.0000

Data Index: 878957 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.9806. Min Act: -0.0000

Data Index: 1298134 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.5915. Min Act: -0.0000

Data Index: 663009 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.4362. Min Act: -0.0000

Data Index: 297400 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.3442. Min Act: -0.0001

Data Index: 128841 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.3830. Min Act: -0.0000

Data Index: 428507 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.1017. Min Act: -0.0000

Data Index: 1123481 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.2813. Min Act: -0.0000

Data Index: 776065 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.1308. Min Act: -0.0000

Data Index: 763348 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.3687. Min Act: -0.0000

Data Index: 1151955 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.2393. Min Act: -0.0000

Data Index: 339171 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.2093. Min Act: -0.0000

Data Index: 1095938 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.2759. Min Act: -0.0000

Data Index: 519346 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.2785. Min Act: -0.0000

Data Index: 308424 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.1462. Min Act: -0.0000

Data Index: 513332 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.0282. Min Act: -0.0000

Data Index: 889245 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.1448. Min Act: -0.0000

Data Index: 1329537 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.1380. Min Act: -0.0000

Data Index: 965828 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.0944. Min Act: -0.0000

Data Index: 178136 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 4.0819. Min Range: -4.0819

Max Act: 2.0782. Min Act: -0.0000

Data Index: 732904 (C4 (Web Text))

Max Activating Token Index: 948