Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 626 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.6595. Min Act: -0.0002

Data Index: 471535 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.6159. Min Act: -0.0003

Data Index: 1084073 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5813. Min Act: -0.0003

Data Index: 1120037 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5644. Min Act: -0.0002

Data Index: 671955 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5563. Min Act: -0.0003

Data Index: 1138193 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5544. Min Act: -0.0002

Data Index: 138797 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5503. Min Act: -0.0003

Data Index: 66840 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5480. Min Act: -0.0003

Data Index: 1027857 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5430. Min Act: -0.0002

Data Index: 652486 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5340. Min Act: -0.0003

Data Index: 853210 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5241. Min Act: -0.0003

Data Index: 480056 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5479. Min Act: -0.0003

Data Index: 266411 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5089. Min Act: -0.0003

Data Index: 2719 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5072. Min Act: -0.0002

Data Index: 695669 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5005. Min Act: -0.0003

Data Index: 420110 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5210. Min Act: -0.0003

Data Index: 606532 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4867. Min Act: -0.0002

Data Index: 1072338 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4832. Min Act: -0.0003

Data Index: 729884 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4825. Min Act: -0.0003

Data Index: 197017 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4762. Min Act: -0.0003

Data Index: 1101611 (C4 (Web Text))

Max Activating Token Index: 109