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

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

Neuron 2643 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1484. Min Act: -0.0000

Data Index: 104587 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1381. Min Act: -0.0000

Data Index: 438869 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1173. Min Act: -0.0000

Data Index: 152679 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1134. Min Act: -0.0000

Data Index: 741357 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1054. Min Act: -0.0000

Data Index: 703577 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1004. Min Act: -0.0000

Data Index: 346512 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1100457 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1170610 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1049. Min Act: -0.0000

Data Index: 439350 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1014. Min Act: -0.0000

Data Index: 986650 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1036. Min Act: -0.0000

Data Index: 674547 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1168382 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1018839 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.0946. Min Act: -0.0000

Data Index: 236422 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.0968. Min Act: -0.0000

Data Index: 492573 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.0985. Min Act: -0.0000

Data Index: 389921 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1036. Min Act: -0.0000

Data Index: 684784 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.0915. Min Act: -0.0000

Data Index: 329680 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.0947. Min Act: -0.0000

Data Index: 829354 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.0943. Min Act: -0.0000

Data Index: 22255 (C4 (Web Text))

Max Activating Token Index: 851