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

Dataset: The Pile

Neuron 892 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: 1.2769. Min Range: -1.2769

Max Act: 1.2769. Min Act: -0.0000

Data Index: 1846586 (The Pile)

Max Activating Token Index: 902

Text #1

Max Range: 1.2769. Min Range: -1.2769

Max Act: 1.1582. Min Act: -0.0000

Data Index: 1665821 (The Pile)

Max Activating Token Index: 945

Text #2

Max Range: 1.2769. Min Range: -1.2769

Max Act: 1.0333. Min Act: -0.0000

Data Index: 400137 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 1.2769. Min Range: -1.2769

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1127472 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 1.2769. Min Range: -1.2769

Max Act: 1.1185. Min Act: -0.0000

Data Index: 841655 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 1.2769. Min Range: -1.2769

Max Act: 1.0165. Min Act: -0.0000

Data Index: 203346 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1534925 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.9690. Min Act: -0.0000

Data Index: 427679 (The Pile)

Max Activating Token Index: 950

Text #8

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1109107 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1532991 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.9936. Min Act: -0.0000

Data Index: 965445 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1950702 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 1.2769. Min Range: -1.2769

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1468301 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1094046 (The Pile)

Max Activating Token Index: 844

Text #14

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.9716. Min Act: -0.0000

Data Index: 968898 (The Pile)

Max Activating Token Index: 683

Text #15

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1924609 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1565291 (The Pile)

Max Activating Token Index: 588

Text #17

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.9620. Min Act: -0.0000

Data Index: 903624 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.8614. Min Act: -0.0000

Data Index: 474842 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 1.2769. Min Range: -1.2769

Max Act: 0.9283. Min Act: -0.0000

Data Index: 772070 (The Pile)

Max Activating Token Index: 825