Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2254 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.1426. Min Act: -0.0000

Data Index: 1092754 (The Pile)

Max Activating Token Index: 869

Text #1

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.1620. Min Act: -0.0000

Data Index: 698746 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1554549 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.0758. Min Act: -0.0000

Data Index: 353582 (The Pile)

Max Activating Token Index: 646

Text #4

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.1070. Min Act: -0.0000

Data Index: 880427 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.0486. Min Act: -0.0000

Data Index: 882050 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.0055. Min Act: -0.0000

Data Index: 149920 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1006856 (The Pile)

Max Activating Token Index: 978

Text #8

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9520. Min Act: -0.0000

Data Index: 710428 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1619421 (The Pile)

Max Activating Token Index: 695

Text #10

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1056171 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9872. Min Act: -0.0000

Data Index: 948917 (The Pile)

Max Activating Token Index: 798

Text #12

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9679. Min Act: -0.0000

Data Index: 2619 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9621. Min Act: -0.0000

Data Index: 814684 (The Pile)

Max Activating Token Index: 848

Text #14

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1173128 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9816. Min Act: -0.0000

Data Index: 1055262 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9024. Min Act: -0.0000

Data Index: 285217 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9194. Min Act: -0.0000

Data Index: 326124 (The Pile)

Max Activating Token Index: 509

Text #18

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9419. Min Act: -0.0000

Data Index: 499348 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9141. Min Act: -0.0000

Data Index: 661612 (The Pile)

Max Activating Token Index: 947