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

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

Neuron 593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1255685 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0965. Min Act: -0.0002

Data Index: 713578 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1134. Min Act: -0.0003

Data Index: 1050773 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0932. Min Act: -0.0003

Data Index: 979796 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0991. Min Act: -0.0002

Data Index: 948664 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0890. Min Act: -0.0002

Data Index: 455246 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0945. Min Act: -0.0002

Data Index: 854128 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0902. Min Act: -0.0003

Data Index: 422921 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1343396 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0891. Min Act: -0.0002

Data Index: 115072 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0881. Min Act: -0.0002

Data Index: 163690 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0897. Min Act: -0.0002

Data Index: 979073 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0825. Min Act: -0.0003

Data Index: 595601 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1277416 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0906. Min Act: -0.0002

Data Index: 146705 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1215334 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0828. Min Act: -0.0002

Data Index: 887811 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1172989 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0829. Min Act: -0.0002

Data Index: 795346 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0837. Min Act: -0.0002

Data Index: 582008 (C4 (Web Text))

Max Activating Token Index: 536