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

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

Neuron 562 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: 0.5543. Min Range: -0.5543

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1152007 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5273. Min Act: -0.0000

Data Index: 36973 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5090. Min Act: -0.0000

Data Index: 444639 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4702. Min Act: -0.0000

Data Index: 758384 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4534. Min Act: -0.0000

Data Index: 104822 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4463. Min Act: -0.0000

Data Index: 719617 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3994. Min Act: -0.0000

Data Index: 462809 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1166751 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1274495 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4549. Min Act: -0.0000

Data Index: 96662 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1338564 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1028045 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4138. Min Act: -0.0000

Data Index: 637653 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1292924 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4097. Min Act: -0.0000

Data Index: 621734 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1141822 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1347296 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1254348 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4042. Min Act: -0.0000

Data Index: 648431 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3880. Min Act: -0.0000

Data Index: 688814 (C4 (Web Text))

Max Activating Token Index: 285