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

Dataset: The Pile

Neuron 2168 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: 1.1011. Min Range: -1.1011

Max Act: 1.1011. Min Act: -0.0000

Data Index: 1129289 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0757. Min Act: -0.0000

Data Index: 932129 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1655115 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0497. Min Act: -0.0000

Data Index: 972512 (The Pile)

Max Activating Token Index: 799

Text #4

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1858229 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1926983 (The Pile)

Max Activating Token Index: 495

Text #6

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0101. Min Act: -0.0000

Data Index: 254455 (The Pile)

Max Activating Token Index: 602

Text #7

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0399. Min Act: -0.0000

Data Index: 1271359 (The Pile)

Max Activating Token Index: 514

Text #8

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9591. Min Act: -0.0000

Data Index: 809005 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9956. Min Act: -0.0000

Data Index: 49230 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0147. Min Act: -0.0000

Data Index: 32215 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0039. Min Act: -0.0000

Data Index: 993573 (The Pile)

Max Activating Token Index: 240

Text #12

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1669827 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9559. Min Act: -0.0000

Data Index: 151576 (The Pile)

Max Activating Token Index: 785

Text #14

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1947474 (The Pile)

Max Activating Token Index: 35

Text #15

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0227. Min Act: -0.0000

Data Index: 1012940 (The Pile)

Max Activating Token Index: 869

Text #16

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9737. Min Act: -0.0000

Data Index: 381224 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9914. Min Act: -0.0000

Data Index: 835301 (The Pile)

Max Activating Token Index: 563

Text #18

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9732. Min Act: -0.0000

Data Index: 235601 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1997683 (The Pile)

Max Activating Token Index: 179