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

Dataset: The Pile

Neuron 1659 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: 0.7172. Min Range: -0.7172

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1819618 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6385. Min Act: -0.0000

Data Index: 578308 (The Pile)

Max Activating Token Index: 564

Text #2

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1287065 (The Pile)

Max Activating Token Index: 376

Text #3

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1186326 (The Pile)

Max Activating Token Index: 684

Text #4

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1133332 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1654589 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1187261 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1649823 (The Pile)

Max Activating Token Index: 724

Text #8

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5906. Min Act: -0.0000

Data Index: 264638 (The Pile)

Max Activating Token Index: 489

Text #9

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1211459 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5856. Min Act: -0.0000

Data Index: 911852 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6015. Min Act: -0.0000

Data Index: 152218 (The Pile)

Max Activating Token Index: 280

Text #12

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1158306 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5849. Min Act: -0.0000

Data Index: 378513 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1866880 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1116647 (The Pile)

Max Activating Token Index: 729

Text #16

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1346669 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6053. Min Act: -0.0000

Data Index: 569994 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5380. Min Act: -0.0000

Data Index: 321630 (The Pile)

Max Activating Token Index: 956

Text #19

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1271957 (The Pile)

Max Activating Token Index: 801