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

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

Neuron 3967 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2646. Min Act: -0.0002

Data Index: 953715 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2574. Min Act: -0.0002

Data Index: 117908 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2563. Min Act: -0.0002

Data Index: 77744 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2372. Min Act: -0.0002

Data Index: 550243 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2359. Min Act: -0.0002

Data Index: 548286 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2308. Min Act: -0.0002

Data Index: 545329 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2265. Min Act: -0.0002

Data Index: 508611 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2129. Min Act: -0.0002

Data Index: 658532 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2114. Min Act: -0.0002

Data Index: 743193 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2065. Min Act: -0.0002

Data Index: 80686 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2058. Min Act: -0.0002

Data Index: 1265702 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2052. Min Act: -0.0002

Data Index: 550337 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2017. Min Act: -0.0002

Data Index: 230381 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1918. Min Act: -0.0002

Data Index: 1018657 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1975. Min Act: -0.0002

Data Index: 566354 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2043. Min Act: -0.0002

Data Index: 278220 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1961. Min Act: -0.0002

Data Index: 1162920 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1933. Min Act: -0.0002

Data Index: 529555 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1932. Min Act: -0.0002

Data Index: 842424 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1930. Min Act: -0.0002

Data Index: 1117896 (C4 (Web Text))

Max Activating Token Index: 16