Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1716 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1066751 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1155. Min Act: -0.0004

Data Index: 128867 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1084. Min Act: -0.0003

Data Index: 1439693 (Python Code)

Max Activating Token Index: 640

Text #3

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1048. Min Act: -0.0004

Data Index: 1001237 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0941. Min Act: -0.0002

Data Index: 1633691 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1634254 (Python Code)

Max Activating Token Index: 305

Text #6

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0915. Min Act: -0.0004

Data Index: 1641642 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0925. Min Act: -0.0003

Data Index: 374222 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1123770 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0881. Min Act: -0.0003

Data Index: 541477 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0899. Min Act: -0.0003

Data Index: 146265 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1640971 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1339817 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0864. Min Act: -0.0002

Data Index: 861719 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0825. Min Act: -0.0003

Data Index: 913687 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0857. Min Act: -0.0003

Data Index: 1449824 (Python Code)

Max Activating Token Index: 476

Text #16

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0851. Min Act: -0.0003

Data Index: 179256 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0828. Min Act: -0.0003

Data Index: 328031 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0848. Min Act: -0.0002

Data Index: 965139 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0820. Min Act: -0.0003

Data Index: 47561 (C4 (Web Text))

Max Activating Token Index: 366