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

Dataset: The Pile

Neuron 966 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.5049. Min Act: 0.0000

Data Index: 1217286 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1558332 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1005621 (The Pile)

Max Activating Token Index: 550

Text #3

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1606784 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1014647 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.5237. Min Act: -0.0000

Data Index: 258118 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.5178. Min Act: -0.0000

Data Index: 336431 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1504372 (The Pile)

Max Activating Token Index: 724

Text #8

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4432. Min Act: -0.0000

Data Index: 874097 (The Pile)

Max Activating Token Index: 151

Text #9

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3967. Min Act: -0.0000

Data Index: 182853 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1118012 (The Pile)

Max Activating Token Index: 111

Text #11

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4601. Min Act: 0.0000

Data Index: 567966 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4432. Min Act: -0.0000

Data Index: 386625 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1348964 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4364. Min Act: -0.0000

Data Index: 218411 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1064273 (The Pile)

Max Activating Token Index: 690

Text #16

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4359. Min Act: -0.0000

Data Index: 204704 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4099. Min Act: -0.0000

Data Index: 88915 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4214. Min Act: -0.0000

Data Index: 294907 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1310587 (The Pile)

Max Activating Token Index: 71