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

Dataset: The Pile

Neuron 890 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.5713. Min Act: -0.0000

Data Index: 1403701 (The Pile)

Max Activating Token Index: 748

Text #1

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.5142. Min Act: -0.0000

Data Index: 1972481 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4780. Min Act: -0.0000

Data Index: 1609328 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4704. Min Act: -0.0000

Data Index: 1554911 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4401. Min Act: -0.0000

Data Index: 898466 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.5296. Min Act: -0.0000

Data Index: 1401392 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4555. Min Act: -0.0000

Data Index: 792611 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4041. Min Act: -0.0000

Data Index: 1458607 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3970. Min Act: -0.0000

Data Index: 79266 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1526370 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1171491 (The Pile)

Max Activating Token Index: 867

Text #11

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3642. Min Act: -0.0000

Data Index: 303515 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3378. Min Act: -0.0000

Data Index: 373568 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3657. Min Act: -0.0000

Data Index: 1183488 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.2711. Min Act: -0.0000

Data Index: 548510 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3096. Min Act: -0.0000

Data Index: 134093 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1144436 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3376. Min Act: -0.0000

Data Index: 585856 (The Pile)

Max Activating Token Index: 27

Text #18

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1758993 (The Pile)

Max Activating Token Index: 89

Text #19

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3304. Min Act: -0.0000

Data Index: 1795989 (The Pile)

Max Activating Token Index: 165