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

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

Neuron 4546 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: 0.1039. Min Range: -0.1039

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1109280 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0923. Min Act: -0.0000

Data Index: 45575 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0853. Min Act: -0.0000

Data Index: 245355 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0881. Min Act: -0.0000

Data Index: 576085 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0861. Min Act: -0.0000

Data Index: 753286 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0887. Min Act: -0.0000

Data Index: 577238 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1178398 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1128938 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1210389 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0799. Min Act: -0.0000

Data Index: 85556 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0854. Min Act: -0.0000

Data Index: 469100 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0844. Min Act: -0.0000

Data Index: 52595 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0785. Min Act: -0.0000

Data Index: 595160 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0801. Min Act: -0.0000

Data Index: 718393 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0770. Min Act: -0.0000

Data Index: 254564 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1339313 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0798. Min Act: -0.0000

Data Index: 934481 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0796. Min Act: -0.0000

Data Index: 965616 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0769. Min Act: -0.0000

Data Index: 948393 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1382669 (Python Code)

Max Activating Token Index: 323