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

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

Neuron 1026 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: 0.1353. Min Range: -0.1353

Max Act: 0.1353. Min Act: -0.0003

Data Index: 1120585 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0916. Min Act: -0.0003

Data Index: 145139 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0935. Min Act: -0.0004

Data Index: 57069 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1240228 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0871. Min Act: -0.0003

Data Index: 42376 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0921. Min Act: -0.0003

Data Index: 378210 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0869. Min Act: -0.0003

Data Index: 70089 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0837. Min Act: -0.0003

Data Index: 1294273 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0825. Min Act: -0.0003

Data Index: 979638 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0798. Min Act: -0.0003

Data Index: 1339776 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0812. Min Act: -0.0004

Data Index: 377858 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0811. Min Act: -0.0003

Data Index: 1166299 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0785. Min Act: -0.0003

Data Index: 812648 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0791. Min Act: -0.0003

Data Index: 532195 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0790. Min Act: -0.0004

Data Index: 1041471 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0790. Min Act: -0.0003

Data Index: 155149 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0789. Min Act: -0.0003

Data Index: 691235 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0802. Min Act: -0.0003

Data Index: 887191 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0769. Min Act: -0.0003

Data Index: 944976 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0785. Min Act: -0.0003

Data Index: 1090645 (C4 (Web Text))

Max Activating Token Index: 961