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

Dataset: The Pile

Neuron 3988 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.7201. Min Act: -0.0000

Data Index: 544022 (The Pile)

Max Activating Token Index: 718

Text #1

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1561981 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.7151. Min Act: -0.0000

Data Index: 22369 (The Pile)

Max Activating Token Index: 562

Text #3

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1180505 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1281733 (The Pile)

Max Activating Token Index: 154

Text #5

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6105. Min Act: -0.0000

Data Index: 992900 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1692261 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6084. Min Act: -0.0000

Data Index: 715690 (The Pile)

Max Activating Token Index: 751

Text #8

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5821. Min Act: -0.0000

Data Index: 528974 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1011691 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1109089 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1540889 (The Pile)

Max Activating Token Index: 579

Text #12

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5460. Min Act: -0.0000

Data Index: 17231 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5299. Min Act: -0.0000

Data Index: 298855 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5294. Min Act: -0.0000

Data Index: 858646 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5097. Min Act: -0.0000

Data Index: 121554 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5383. Min Act: -0.0000

Data Index: 727316 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1856389 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5113. Min Act: -0.0000

Data Index: 280450 (The Pile)

Max Activating Token Index: 586

Text #19

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5056. Min Act: -0.0000

Data Index: 540970 (The Pile)

Max Activating Token Index: 5