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

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

Neuron 547 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: 0.1262. Min Range: -0.1262

Max Act: 0.1262. Min Act: -0.0000

Data Index: 538663 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1027. Min Act: -0.0000

Data Index: 852296 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0952. Min Act: -0.0000

Data Index: 835958 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0945. Min Act: -0.0000

Data Index: 225623 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0937. Min Act: -0.0000

Data Index: 467500 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1102277 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1251849 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0829. Min Act: -0.0000

Data Index: 260711 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0869. Min Act: -0.0000

Data Index: 373091 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0790. Min Act: -0.0000

Data Index: 318246 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0786. Min Act: -0.0000

Data Index: 669169 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0892. Min Act: -0.0000

Data Index: 548193 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0826. Min Act: -0.0000

Data Index: 822120 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0779. Min Act: -0.0000

Data Index: 965831 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0773. Min Act: -0.0000

Data Index: 640127 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0737. Min Act: -0.0000

Data Index: 600256 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0718. Min Act: -0.0000

Data Index: 759837 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0756. Min Act: -0.0000

Data Index: 619174 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0720. Min Act: -0.0000

Data Index: 726167 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1039153 (C4 (Web Text))

Max Activating Token Index: 139