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

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

Neuron 1767 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: 0.1166. Min Range: -0.1166

Max Act: 0.1166. Min Act: -0.0002

Data Index: 885549 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1063. Min Act: -0.0002

Data Index: 531218 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1098. Min Act: -0.0002

Data Index: 228198 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1002167 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0904. Min Act: -0.0002

Data Index: 431011 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0959. Min Act: -0.0002

Data Index: 394500 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0917. Min Act: -0.0002

Data Index: 274372 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0928. Min Act: -0.0002

Data Index: 65910 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0876. Min Act: -0.0002

Data Index: 334770 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0909. Min Act: -0.0002

Data Index: 784675 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0941. Min Act: -0.0002

Data Index: 1070371 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0869. Min Act: -0.0002

Data Index: 167822 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0778. Min Act: -0.0002

Data Index: 427838 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0837. Min Act: -0.0002

Data Index: 478100 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0892. Min Act: -0.0002

Data Index: 814447 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0859. Min Act: -0.0002

Data Index: 522201 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0890. Min Act: -0.0002

Data Index: 385639 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0845. Min Act: -0.0002

Data Index: 890910 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0872. Min Act: -0.0002

Data Index: 351115 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1249352 (C4 (Web Text))

Max Activating Token Index: 402