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

Dataset: The Pile

Neuron 846 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: 5.0760. Min Range: -5.0760

Max Act: 5.0760. Min Act: -0.0000

Data Index: 310170 (The Pile)

Max Activating Token Index: 947

Text #1

Max Range: 5.0760. Min Range: -5.0760

Max Act: 3.6221. Min Act: -0.0000

Data Index: 349093 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 5.0760. Min Range: -5.0760

Max Act: 3.2648. Min Act: -0.0000

Data Index: 210388 (The Pile)

Max Activating Token Index: 946

Text #3

Max Range: 5.0760. Min Range: -5.0760

Max Act: 3.0797. Min Act: -0.0000

Data Index: 21697 (The Pile)

Max Activating Token Index: 683

Text #4

Max Range: 5.0760. Min Range: -5.0760

Max Act: 3.3146. Min Act: -0.0000

Data Index: 693046 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 5.0760. Min Range: -5.0760

Max Act: 3.1597. Min Act: -0.0000

Data Index: 323774 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 5.0760. Min Range: -5.0760

Max Act: 3.3000. Min Act: -0.0000

Data Index: 775897 (The Pile)

Max Activating Token Index: 906

Text #7

Max Range: 5.0760. Min Range: -5.0760

Max Act: 2.8679. Min Act: -0.0000

Data Index: 16691 (The Pile)

Max Activating Token Index: 891

Text #8

Max Range: 5.0760. Min Range: -5.0760

Max Act: 2.9915. Min Act: -0.0000

Data Index: 503085 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 5.0760. Min Range: -5.0760

Max Act: 3.1092. Min Act: -0.0000

Data Index: 462459 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 5.0760. Min Range: -5.0760

Max Act: 2.6709. Min Act: -0.0000

Data Index: 694940 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 5.0760. Min Range: -5.0760

Max Act: 2.9240. Min Act: -0.0000

Data Index: 378106 (The Pile)

Max Activating Token Index: 850

Text #12

Max Range: 5.0760. Min Range: -5.0760

Max Act: 3.0663. Min Act: -0.0000

Data Index: 733672 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 5.0760. Min Range: -5.0760

Max Act: 3.1821. Min Act: -0.0000

Data Index: 1762811 (The Pile)

Max Activating Token Index: 981

Text #14

Max Range: 5.0760. Min Range: -5.0760

Max Act: 3.0375. Min Act: -0.0000

Data Index: 1128333 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 5.0760. Min Range: -5.0760

Max Act: 2.6105. Min Act: -0.0000

Data Index: 58848 (The Pile)

Max Activating Token Index: 767

Text #16

Max Range: 5.0760. Min Range: -5.0760

Max Act: 2.5988. Min Act: -0.0000

Data Index: 854856 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 5.0760. Min Range: -5.0760

Max Act: 3.0112. Min Act: -0.0000

Data Index: 821503 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 5.0760. Min Range: -5.0760

Max Act: 2.8405. Min Act: -0.0000

Data Index: 1306380 (The Pile)

Max Activating Token Index: 992

Text #19

Max Range: 5.0760. Min Range: -5.0760

Max Act: 2.8033. Min Act: -0.0000

Data Index: 582643 (The Pile)

Max Activating Token Index: 830