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

Dataset: The Pile

Neuron 601 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.1243. Min Act: -0.0000

Data Index: 521502 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0039. Min Act: -0.0000

Data Index: 94139 (The Pile)

Max Activating Token Index: 593

Text #2

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1359423 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1101516 (The Pile)

Max Activating Token Index: 726

Text #4

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9811. Min Act: -0.0000

Data Index: 340042 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1723647 (The Pile)

Max Activating Token Index: 601

Text #6

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1861482 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1756138 (The Pile)

Max Activating Token Index: 301

Text #8

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9302. Min Act: -0.0000

Data Index: 1907526 (The Pile)

Max Activating Token Index: 775

Text #9

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9497. Min Act: -0.0000

Data Index: 392063 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9000. Min Act: -0.0000

Data Index: 478417 (The Pile)

Max Activating Token Index: 767

Text #11

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1525571 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1359614 (The Pile)

Max Activating Token Index: 366

Text #13

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8565. Min Act: -0.0000

Data Index: 784756 (The Pile)

Max Activating Token Index: 609

Text #14

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1899862 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8780. Min Act: -0.0000

Data Index: 827528 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8770. Min Act: -0.0000

Data Index: 377878 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1210622 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1819123 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9295. Min Act: -0.0000

Data Index: 789624 (The Pile)

Max Activating Token Index: 888