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

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

Neuron 3780 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6811. Min Act: -0.0000

Data Index: 536684 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4615. Min Act: -0.0000

Data Index: 226889 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.5239. Min Act: -0.0000

Data Index: 512155 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4348. Min Act: -0.0001

Data Index: 1324655 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4224. Min Act: -0.0000

Data Index: 877052 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4921. Min Act: -0.0001

Data Index: 1055156 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1053540 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4147. Min Act: -0.0000

Data Index: 651996 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1920. Min Act: -0.0000

Data Index: 1088777 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2076. Min Act: -0.0000

Data Index: 950843 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2093. Min Act: -0.0000

Data Index: 778398 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1961. Min Act: -0.0000

Data Index: 367570 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.0575. Min Act: -0.0000

Data Index: 952612 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2214. Min Act: -0.0000

Data Index: 277692 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2119. Min Act: -0.0001

Data Index: 785233 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1528. Min Act: -0.0000

Data Index: 472885 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1066363 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1383. Min Act: -0.0000

Data Index: 248293 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.0832. Min Act: -0.0000

Data Index: 628184 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1446. Min Act: -0.0000

Data Index: 851459 (C4 (Web Text))

Max Activating Token Index: 300