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

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

Neuron 245 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: 3.6879. Min Range: -3.6879

Max Act: 3.6879. Min Act: -0.0000

Data Index: 973405 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.1202. Min Act: -0.0000

Data Index: 38313 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.2163. Min Act: -0.0000

Data Index: 991302 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.9672. Min Act: -0.0000

Data Index: 1021887 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.0959. Min Act: -0.0000

Data Index: 356835 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.9478. Min Act: -0.0000

Data Index: 302600 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.9068. Min Act: -0.0000

Data Index: 696358 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.7187. Min Act: -0.0000

Data Index: 796849 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.8251. Min Act: -0.0000

Data Index: 1204686 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.6608. Min Act: -0.0000

Data Index: 834575 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.7856. Min Act: -0.0000

Data Index: 430867 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.7533. Min Act: -0.0000

Data Index: 1005203 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.6745. Min Act: -0.0000

Data Index: 814486 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.5360. Min Act: -0.0000

Data Index: 1211636 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.4136. Min Act: -0.0000

Data Index: 557833 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.6873. Min Act: -0.0000

Data Index: 1037836 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.5388. Min Act: -0.0000

Data Index: 415256 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.5233. Min Act: -0.0000

Data Index: 1113960 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.4861. Min Act: -0.0000

Data Index: 265204 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 3.6879. Min Range: -3.6879

Max Act: 2.3604. Min Act: -0.0000

Data Index: 55154 (C4 (Web Text))

Max Activating Token Index: 448