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

Dataset: The Pile

Neuron 1118 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1398. Min Act: -0.0000

Data Index: 561142 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1500520 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1503893 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1116. Min Act: -0.0000

Data Index: 363870 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1283736 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1846235 (The Pile)

Max Activating Token Index: 890

Text #6

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0929. Min Act: -0.0000

Data Index: 845720 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0892. Min Act: -0.0000

Data Index: 513835 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0873. Min Act: -0.0000

Data Index: 26395 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0874. Min Act: -0.0000

Data Index: 378533 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0765. Min Act: -0.0000

Data Index: 351728 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0864. Min Act: -0.0000

Data Index: 428936 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0796. Min Act: -0.0000

Data Index: 295028 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0795. Min Act: -0.0000

Data Index: 249310 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1551133 (The Pile)

Max Activating Token Index: 897

Text #15

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0799. Min Act: -0.0000

Data Index: 895881 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0797. Min Act: -0.0000

Data Index: 738775 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0820. Min Act: -0.0000

Data Index: 796879 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0783. Min Act: -0.0000

Data Index: 106812 (The Pile)

Max Activating Token Index: 807

Text #19

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1825030 (The Pile)

Max Activating Token Index: 737