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

Dataset: The Pile

Neuron 2846 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1531901 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1389212 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9771. Min Act: -0.0000

Data Index: 734516 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1132096 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1775157 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0054. Min Act: -0.0000

Data Index: 284671 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1321025 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9304. Min Act: -0.0001

Data Index: 29502 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1943655 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1464616 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9210. Min Act: -0.0001

Data Index: 734840 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9196. Min Act: -0.0000

Data Index: 1668898 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1266505 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1808373 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9272. Min Act: -0.0000

Data Index: 760696 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8815. Min Act: -0.0000

Data Index: 210879 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8493. Min Act: -0.0000

Data Index: 110902 (The Pile)

Max Activating Token Index: 195

Text #17

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1015437 (The Pile)

Max Activating Token Index: 765

Text #18

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8264. Min Act: -0.0000

Data Index: 479565 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1003324 (The Pile)

Max Activating Token Index: 678