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

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

Neuron 3921 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: 0.3850. Min Range: -0.3850

Max Act: 0.3850. Min Act: -0.0000

Data Index: 303397 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3620. Min Act: -0.0000

Data Index: 255002 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1146750 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3350. Min Act: -0.0000

Data Index: 127810 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2918. Min Act: -0.0000

Data Index: 1068269 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2846. Min Act: -0.0001

Data Index: 143404 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2758. Min Act: -0.0000

Data Index: 494413 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3050. Min Act: -0.0000

Data Index: 519287 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3016. Min Act: -0.0000

Data Index: 291713 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2724. Min Act: -0.0001

Data Index: 1162650 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2666. Min Act: -0.0000

Data Index: 506813 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2702. Min Act: -0.0001

Data Index: 699685 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2579. Min Act: -0.0000

Data Index: 466471 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2676. Min Act: -0.0000

Data Index: 704456 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2663. Min Act: -0.0000

Data Index: 81096 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2685. Min Act: -0.0001

Data Index: 685693 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2581. Min Act: -0.0000

Data Index: 608936 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2653. Min Act: -0.0000

Data Index: 93147 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1009364 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2516. Min Act: -0.0000

Data Index: 448260 (C4 (Web Text))

Max Activating Token Index: 785