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

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

Neuron 4504 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1148. Min Range: -5.1148

Max Act: 4.9716. Min Act: -0.0000

Data Index: 932685 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 5.1148. Min Range: -5.1148

Max Act: 4.7821. Min Act: -0.0000

Data Index: 1268222 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 5.1148. Min Range: -5.1148

Max Act: 5.1148. Min Act: -0.0000

Data Index: 1002016 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 5.1148. Min Range: -5.1148

Max Act: 4.7932. Min Act: -0.0000

Data Index: 176918 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 5.1148. Min Range: -5.1148

Max Act: 4.7222. Min Act: -0.0000

Data Index: 865049 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 5.1148. Min Range: -5.1148

Max Act: 4.7653. Min Act: -0.0000

Data Index: 46494 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 5.1148. Min Range: -5.1148

Max Act: 4.5730. Min Act: -0.0000

Data Index: 125999 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 5.1148. Min Range: -5.1148

Max Act: 4.2732. Min Act: -0.0000

Data Index: 846426 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 5.1148. Min Range: -5.1148

Max Act: 4.5914. Min Act: -0.0000

Data Index: 757209 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 5.1148. Min Range: -5.1148

Max Act: 4.4471. Min Act: -0.0000

Data Index: 1098918 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 5.1148. Min Range: -5.1148

Max Act: 3.4104. Min Act: -0.0000

Data Index: 849427 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 5.1148. Min Range: -5.1148

Max Act: 3.0728. Min Act: -0.0000

Data Index: 602720 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 5.1148. Min Range: -5.1148

Max Act: 3.0066. Min Act: -0.0000

Data Index: 131750 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 5.1148. Min Range: -5.1148

Max Act: 2.9458. Min Act: -0.0000

Data Index: 111607 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 5.1148. Min Range: -5.1148

Max Act: 3.0387. Min Act: -0.0000

Data Index: 119468 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 5.1148. Min Range: -5.1148

Max Act: 2.9838. Min Act: -0.0000

Data Index: 1238086 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 5.1148. Min Range: -5.1148

Max Act: 2.7159. Min Act: -0.0000

Data Index: 296553 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 5.1148. Min Range: -5.1148

Max Act: 2.7217. Min Act: -0.0000

Data Index: 1330166 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 5.1148. Min Range: -5.1148

Max Act: 2.5736. Min Act: -0.0000

Data Index: 310295 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 5.1148. Min Range: -5.1148

Max Act: 2.5149. Min Act: -0.0000

Data Index: 651723 (C4 (Web Text))

Max Activating Token Index: 463