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

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

Neuron 3289 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: 1.6827. Min Range: -1.6827

Max Act: 1.6827. Min Act: -0.0000

Data Index: 828164 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.3058. Min Act: -0.0000

Data Index: 278999 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.3111. Min Act: -0.0000

Data Index: 1164841 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.3693. Min Act: -0.0000

Data Index: 598154 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.2188. Min Act: -0.0000

Data Index: 333125 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.3606. Min Act: -0.0000

Data Index: 986679 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.3254. Min Act: -0.0000

Data Index: 27544 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.2677. Min Act: -0.0000

Data Index: 318505 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.2886. Min Act: -0.0000

Data Index: 1026428 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1183784 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.2700. Min Act: -0.0000

Data Index: 171884 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.1465. Min Act: -0.0000

Data Index: 310377 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.1556. Min Act: -0.0000

Data Index: 732231 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.2286. Min Act: -0.0000

Data Index: 940066 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.2075. Min Act: -0.0000

Data Index: 67719 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.2048. Min Act: -0.0000

Data Index: 511801 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.2023. Min Act: -0.0000

Data Index: 197213 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.0533. Min Act: -0.0000

Data Index: 324908 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1052826 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.1732. Min Act: -0.0000

Data Index: 1021897 (C4 (Web Text))

Max Activating Token Index: 973