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

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

Neuron 4602 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: 0.1040. Min Range: -0.1040

Max Act: 0.1006. Min Act: -0.0002

Data Index: 439663 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1252805 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1296589 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0972. Min Act: -0.0002

Data Index: 722832 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1038. Min Act: -0.0002

Data Index: 364507 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1010. Min Act: -0.0002

Data Index: 843635 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0889. Min Act: -0.0002

Data Index: 604868 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0963. Min Act: -0.0002

Data Index: 411169 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0885. Min Act: -0.0002

Data Index: 128999 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1020. Min Act: -0.0002

Data Index: 472613 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1317156 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1221881 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0933. Min Act: -0.0002

Data Index: 601684 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0949. Min Act: -0.0002

Data Index: 560291 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0921. Min Act: -0.0002

Data Index: 360515 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0951. Min Act: -0.0002

Data Index: 441513 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0884. Min Act: -0.0002

Data Index: 880362 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0934. Min Act: -0.0002

Data Index: 409507 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0870. Min Act: -0.0002

Data Index: 471168 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0934. Min Act: -0.0002

Data Index: 544276 (C4 (Web Text))

Max Activating Token Index: 1014