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

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

Neuron 1798 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: 1.0006. Min Range: -1.0006

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1200276 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9770. Min Act: -0.0000

Data Index: 60045 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8939. Min Act: -0.0000

Data Index: 722384 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9463. Min Act: -0.0000

Data Index: 459479 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7762. Min Act: -0.0000

Data Index: 720924 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1190609 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7522. Min Act: -0.0000

Data Index: 838281 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7954. Min Act: -0.0000

Data Index: 349773 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1149279 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7482. Min Act: -0.0000

Data Index: 682567 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1206631 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7054. Min Act: -0.0000

Data Index: 340905 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7423. Min Act: -0.0000

Data Index: 286743 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1211133 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7849. Min Act: -0.0000

Data Index: 741031 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1032677 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1181385 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.6819. Min Act: -0.0000

Data Index: 756630 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.6602. Min Act: -0.0000

Data Index: 306375 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7014. Min Act: -0.0000

Data Index: 544557 (C4 (Web Text))

Max Activating Token Index: 677