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

Dataset: The Pile

Neuron 4461 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: 0.3468. Min Range: -0.3468

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1825924 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.3438. Min Act: -0.0000

Data Index: 742101 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1841728 (The Pile)

Max Activating Token Index: 562

Text #3

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1932195 (The Pile)

Max Activating Token Index: 594

Text #4

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1663364 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1647359 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1690657 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2027. Min Act: -0.0000

Data Index: 761958 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1827028 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2286. Min Act: -0.0000

Data Index: 792531 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1014316 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2002. Min Act: -0.0000

Data Index: 275046 (The Pile)

Max Activating Token Index: 690

Text #12

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1939526 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2257. Min Act: -0.0000

Data Index: 683479 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2146. Min Act: -0.0000

Data Index: 1108484 (The Pile)

Max Activating Token Index: 771

Text #15

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1876534 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1604615 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1231557 (The Pile)

Max Activating Token Index: 769

Text #18

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1898. Min Act: -0.0000

Data Index: 927273 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1065212 (The Pile)

Max Activating Token Index: 595