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

Dataset: The Pile

Neuron 1346 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: 0.3246. Min Range: -0.3246

Max Act: 0.3178. Min Act: -0.0000

Data Index: 372785 (The Pile)

Max Activating Token Index: 416

Text #1

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1489634 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1354107 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2608. Min Act: -0.0000

Data Index: 682222 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1060842 (The Pile)

Max Activating Token Index: 816

Text #5

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2091. Min Act: -0.0000

Data Index: 393779 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2224. Min Act: -0.0000

Data Index: 771363 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2225. Min Act: -0.0000

Data Index: 86645 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2204. Min Act: -0.0000

Data Index: 431862 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1993. Min Act: -0.0000

Data Index: 100674 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2170. Min Act: -0.0000

Data Index: 602324 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1252317 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1444687 (The Pile)

Max Activating Token Index: 176

Text #13

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1719907 (The Pile)

Max Activating Token Index: 813

Text #14

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1934. Min Act: -0.0000

Data Index: 320454 (The Pile)

Max Activating Token Index: 579

Text #15

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1997756 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1336099 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2048. Min Act: -0.0000

Data Index: 319041 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1141111 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1962. Min Act: -0.0000

Data Index: 384151 (The Pile)

Max Activating Token Index: 593