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

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

Neuron 4267 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: 1.0417. Min Range: -1.0417

Max Act: 1.0417. Min Act: -0.0000

Data Index: 226025 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.0417. Min Range: -1.0417

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1236138 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.7389. Min Act: -0.0000

Data Index: 723310 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.6546. Min Act: -0.0000

Data Index: 789607 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.5666. Min Act: -0.0000

Data Index: 271891 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.5256. Min Act: 0.0000

Data Index: 940841 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.5157. Min Act: -0.0000

Data Index: 846319 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.5035. Min Act: -0.0000

Data Index: 185648 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.5185. Min Act: -0.0000

Data Index: 978654 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.5096. Min Act: -0.0000

Data Index: 630308 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.4765. Min Act: -0.0000

Data Index: 290616 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.5011. Min Act: -0.0000

Data Index: 760568 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.4656. Min Act: -0.0000

Data Index: 499214 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.4644. Min Act: -0.0000

Data Index: 977204 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.5102. Min Act: -0.0000

Data Index: 708381 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1455019 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.4291. Min Act: -0.0000

Data Index: 571329 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1081517 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1073686 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.4185. Min Act: -0.0000

Data Index: 743564 (C4 (Web Text))

Max Activating Token Index: 772