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

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

Neuron 1129 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5796. Min Act: -0.0000

Data Index: 241816 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1044959 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5178. Min Act: -0.0000

Data Index: 278860 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4836. Min Act: -0.0000

Data Index: 693472 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4778. Min Act: -0.0000

Data Index: 172656 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4566. Min Act: -0.0000

Data Index: 508127 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4795. Min Act: -0.0000

Data Index: 845524 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4478. Min Act: -0.0000

Data Index: 556828 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4546. Min Act: -0.0000

Data Index: 153308 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4675. Min Act: -0.0000

Data Index: 566681 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4118. Min Act: -0.0000

Data Index: 565092 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4332. Min Act: -0.0000

Data Index: 396834 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4238. Min Act: -0.0000

Data Index: 365283 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4430. Min Act: -0.0000

Data Index: 319365 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4154. Min Act: -0.0000

Data Index: 919404 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4087. Min Act: -0.0000

Data Index: 310076 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4047. Min Act: -0.0000

Data Index: 67633 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.3981. Min Act: -0.0000

Data Index: 548489 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.3873. Min Act: -0.0000

Data Index: 613644 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4092. Min Act: -0.0000

Data Index: 881609 (C4 (Web Text))

Max Activating Token Index: 695