Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 66 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3245. Min Range: -3.3245

Max Act: 3.3245. Min Act: -0.0000

Data Index: 1357602 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 3.3245. Min Range: -3.3245

Max Act: 3.0853. Min Act: -0.0000

Data Index: 521581 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.5888. Min Act: -0.0000

Data Index: 541603 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.4489. Min Act: -0.0000

Data Index: 741956 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.7156. Min Act: -0.0000

Data Index: 381705 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.2489. Min Act: -0.0000

Data Index: 888677 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.4134. Min Act: -0.0000

Data Index: 685214 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.2743. Min Act: -0.0000

Data Index: 269405 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.2819. Min Act: -0.0000

Data Index: 1247288 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.2738. Min Act: -0.0000

Data Index: 844076 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.1504. Min Act: -0.0000

Data Index: 1317729 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.0007. Min Act: -0.0000

Data Index: 1020410 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.1182. Min Act: -0.0000

Data Index: 901690 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 3.3245. Min Range: -3.3245

Max Act: 1.9830. Min Act: -0.0000

Data Index: 1185271 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 3.3245. Min Range: -3.3245

Max Act: 1.9870. Min Act: -0.0000

Data Index: 550112 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.1927. Min Act: -0.0000

Data Index: 752170 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 3.3245. Min Range: -3.3245

Max Act: 1.9966. Min Act: -0.0000

Data Index: 450817 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 3.3245. Min Range: -3.3245

Max Act: 1.9566. Min Act: -0.0000

Data Index: 722425 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 3.3245. Min Range: -3.3245

Max Act: 1.9515. Min Act: -0.0000

Data Index: 454815 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 3.3245. Min Range: -3.3245

Max Act: 2.0448. Min Act: -0.0000

Data Index: 347975 (C4 (Web Text))

Max Activating Token Index: 544