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

Dataset: The Pile

Neuron 1782 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3775. Min Act: -0.0000

Data Index: 138074 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1118829 (The Pile)

Max Activating Token Index: 841

Text #2

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2975. Min Act: 0.0000

Data Index: 296176 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1752844 (The Pile)

Max Activating Token Index: 267

Text #4

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2579. Min Act: -0.0000

Data Index: 619245 (The Pile)

Max Activating Token Index: 822

Text #5

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1353159 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1300353 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1296341 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1496210 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2611. Min Act: -0.0000

Data Index: 1102068 (The Pile)

Max Activating Token Index: 56

Text #10

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1939504 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2546. Min Act: -0.0000

Data Index: 337456 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2715. Min Act: 0.0000

Data Index: 1573738 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2371. Min Act: -0.0000

Data Index: 347995 (The Pile)

Max Activating Token Index: 645

Text #14

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2284. Min Act: -0.0000

Data Index: 921714 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1766536 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1111728 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1314465 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2237. Min Act: -0.0000

Data Index: 146438 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2325. Min Act: -0.0000

Data Index: 888926 (The Pile)

Max Activating Token Index: 932