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

Dataset: The Pile

Neuron 4508 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1953. Min Range: -4.1953

Max Act: 4.1953. Min Act: -0.0000

Data Index: 1316907 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.8494. Min Act: -0.0000

Data Index: 517720 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.9631. Min Act: -0.0000

Data Index: 687722 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.7242. Min Act: -0.0000

Data Index: 1108490 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.2968. Min Act: -0.0000

Data Index: 825964 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.3441. Min Act: -0.0000

Data Index: 957672 (The Pile)

Max Activating Token Index: 553

Text #6

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.3021. Min Act: -0.0000

Data Index: 1562855 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.5951. Min Act: -0.0000

Data Index: 1450598 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.3539. Min Act: -0.0000

Data Index: 501302 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.2579. Min Act: -0.0000

Data Index: 1159452 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.1177. Min Act: -0.0000

Data Index: 775832 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.4676. Min Act: -0.0000

Data Index: 662532 (The Pile)

Max Activating Token Index: 185

Text #12

Max Range: 4.1953. Min Range: -4.1953

Max Act: 2.9916. Min Act: -0.0000

Data Index: 248556 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 4.1953. Min Range: -4.1953

Max Act: 2.9920. Min Act: -0.0000

Data Index: 35857 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.2571. Min Act: -0.0000

Data Index: 1021067 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.1382. Min Act: -0.0000

Data Index: 1861946 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.2529. Min Act: -0.0000

Data Index: 61444 (The Pile)

Max Activating Token Index: 858

Text #17

Max Range: 4.1953. Min Range: -4.1953

Max Act: 2.9781. Min Act: -0.0000

Data Index: 190586 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 4.1953. Min Range: -4.1953

Max Act: 3.1634. Min Act: -0.0000

Data Index: 1804590 (The Pile)

Max Activating Token Index: 324

Text #19

Max Range: 4.1953. Min Range: -4.1953

Max Act: 2.8444. Min Act: -0.0000

Data Index: 843125 (The Pile)

Max Activating Token Index: 988