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

Dataset: The Pile

Neuron 3045 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3871. Min Act: -0.0000

Data Index: 521558 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1489278 (The Pile)

Max Activating Token Index: 661

Text #2

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1104826 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1275417 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1129931 (The Pile)

Max Activating Token Index: 686

Text #5

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3829. Min Act: -0.0000

Data Index: 623798 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3386. Min Act: -0.0000

Data Index: 88812 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1253998 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1953771 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1015421 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1795509 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3451. Min Act: -0.0000

Data Index: 771788 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1966872 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3520. Min Act: -0.0000

Data Index: 579689 (The Pile)

Max Activating Token Index: 242

Text #14

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3605. Min Act: -0.0000

Data Index: 168701 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1847638 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3560. Min Act: -0.0000

Data Index: 903530 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1350337 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1025149 (The Pile)

Max Activating Token Index: 36

Text #19

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1988509 (The Pile)

Max Activating Token Index: 81