Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4965 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.2622. Min Act: -0.0000

Data Index: 1080430 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1933. Min Act: -0.0000

Data Index: 412116 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1346321 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1592. Min Act: -0.0000

Data Index: 1123752 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1796. Min Act: -0.0000

Data Index: 642636 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.2191. Min Act: -0.0000

Data Index: 873753 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1282. Min Act: -0.0000

Data Index: 895 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1494. Min Act: -0.0000

Data Index: 793483 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0427. Min Act: -0.0000

Data Index: 680149 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1074. Min Act: -0.0000

Data Index: 294503 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0278. Min Act: -0.0000

Data Index: 781526 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9631. Min Act: -0.0000

Data Index: 104824 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1526. Min Act: -0.0000

Data Index: 865280 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0291. Min Act: -0.0000

Data Index: 124522 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0132. Min Act: -0.0000

Data Index: 126031 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0454. Min Act: -0.0000

Data Index: 535303 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0498. Min Act: -0.0000

Data Index: 858882 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9775. Min Act: -0.0000

Data Index: 391838 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9783. Min Act: -0.0000

Data Index: 600077 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9762. Min Act: -0.0000

Data Index: 503726 (C4 (Web Text))

Max Activating Token Index: 495