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

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

Neuron 2930 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.9393. Min Act: -0.0000

Data Index: 8245 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8918. Min Act: -0.0000

Data Index: 730388 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.9449. Min Act: -0.0000

Data Index: 669177 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.9399. Min Act: -0.0000

Data Index: 187553 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8831. Min Act: -0.0000

Data Index: 756392 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8760. Min Act: -0.0000

Data Index: 729713 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.9053. Min Act: -0.0000

Data Index: 216275 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8655. Min Act: -0.0000

Data Index: 526102 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8643. Min Act: -0.0000

Data Index: 612151 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1139323 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8482. Min Act: -0.0000

Data Index: 897263 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1094699 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1126355 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8209. Min Act: -0.0000

Data Index: 995672 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8185. Min Act: -0.0000

Data Index: 548882 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8077. Min Act: -0.0000

Data Index: 917264 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1181180 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7763. Min Act: -0.0000

Data Index: 809475 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7749. Min Act: -0.0000

Data Index: 657928 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7976. Min Act: -0.0000

Data Index: 366445 (C4 (Web Text))

Max Activating Token Index: 522