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

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

Neuron 2913 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: 2.1627. Min Range: -2.1627

Max Act: 2.1627. Min Act: -0.0000

Data Index: 833701 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 2.1627. Min Range: -2.1627

Max Act: 2.1280. Min Act: -0.0000

Data Index: 1291304 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 2.1627. Min Range: -2.1627

Max Act: 2.0961. Min Act: -0.0000

Data Index: 748499 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 2.1627. Min Range: -2.1627

Max Act: 2.0825. Min Act: -0.0000

Data Index: 763109 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.9087. Min Act: -0.0000

Data Index: 93509 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.7696. Min Act: -0.0000

Data Index: 1307563 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.9163. Min Act: -0.0000

Data Index: 781763 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.7378. Min Act: -0.0000

Data Index: 1344549 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.7313. Min Act: -0.0000

Data Index: 555860 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.6227. Min Act: -0.0000

Data Index: 417467 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.6798. Min Act: -0.0000

Data Index: 554296 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.6895. Min Act: -0.0000

Data Index: 148578 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.7036. Min Act: -0.0000

Data Index: 713854 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.6211. Min Act: -0.0000

Data Index: 761437 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.5790. Min Act: -0.0000

Data Index: 911267 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.6970. Min Act: -0.0000

Data Index: 540467 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.6538. Min Act: -0.0000

Data Index: 209509 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.7158. Min Act: -0.0000

Data Index: 1149345 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.6177. Min Act: -0.0000

Data Index: 68437 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 2.1627. Min Range: -2.1627

Max Act: 1.6197. Min Act: -0.0000

Data Index: 282596 (C4 (Web Text))

Max Activating Token Index: 500