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

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

Neuron 93 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.5504. Min Act: -0.0002

Data Index: 746660 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4750. Min Act: -0.0002

Data Index: 291518 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.5035. Min Act: -0.0003

Data Index: 1036374 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4782. Min Act: -0.0002

Data Index: 457093 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4760. Min Act: -0.0003

Data Index: 611311 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4680. Min Act: -0.0003

Data Index: 1193512 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4204. Min Act: -0.0003

Data Index: 244073 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4170. Min Act: -0.0003

Data Index: 278098 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4025. Min Act: -0.0002

Data Index: 568818 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3981. Min Act: -0.0003

Data Index: 168127 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3921. Min Act: -0.0002

Data Index: 1208856 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3905. Min Act: -0.0002

Data Index: 602038 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3741. Min Act: -0.0002

Data Index: 1264743 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3820. Min Act: -0.0003

Data Index: 1134056 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3690. Min Act: -0.0002

Data Index: 121050 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3786. Min Act: -0.0003

Data Index: 338694 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3679. Min Act: -0.0003

Data Index: 1091294 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3662. Min Act: -0.0002

Data Index: 78128 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3751. Min Act: -0.0003

Data Index: 96882 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3595. Min Act: -0.0003

Data Index: 700529 (C4 (Web Text))

Max Activating Token Index: 692