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

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

Neuron 1154 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: 1.9695. Min Range: -1.9695

Max Act: 1.9695. Min Act: -0.0001

Data Index: 1351217 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.6971. Min Act: -0.0001

Data Index: 258296 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8029. Min Act: -0.0001

Data Index: 1110937 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.7794. Min Act: -0.0001

Data Index: 522268 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.5371. Min Act: -0.0001

Data Index: 724425 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.5120. Min Act: -0.0001

Data Index: 463897 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.5367. Min Act: -0.0001

Data Index: 976727 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.2920. Min Act: -0.0001

Data Index: 1274588 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.4683. Min Act: -0.0001

Data Index: 4303 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.4657. Min Act: -0.0001

Data Index: 973223 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.3765. Min Act: -0.0001

Data Index: 871556 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.6454. Min Act: -0.0001

Data Index: 681697 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.1543. Min Act: -0.0001

Data Index: 666464 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.4071. Min Act: -0.0001

Data Index: 547987 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.6886. Min Act: -0.0001

Data Index: 656562 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.5369. Min Act: -0.0001

Data Index: 915659 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.5040. Min Act: -0.0001

Data Index: 618580 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.3236. Min Act: -0.0001

Data Index: 790 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.4439. Min Act: -0.0001

Data Index: 1051336 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.4383. Min Act: -0.0001

Data Index: 501678 (C4 (Web Text))

Max Activating Token Index: 309