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

Dataset: The Pile

Neuron 4221 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1765364 (The Pile)

Max Activating Token Index: 947

Text #1

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.3033. Min Act: -0.0000

Data Index: 1658620 (The Pile)

Max Activating Token Index: 694

Text #2

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1095. Min Act: -0.0000

Data Index: 1651474 (The Pile)

Max Activating Token Index: 497

Text #3

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1142886 (The Pile)

Max Activating Token Index: 562

Text #4

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1715. Min Act: -0.0000

Data Index: 427052 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.0886. Min Act: -0.0000

Data Index: 226835 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1143. Min Act: -0.0000

Data Index: 787341 (The Pile)

Max Activating Token Index: 590

Text #7

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1830141 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.0995. Min Act: -0.0000

Data Index: 411660 (The Pile)

Max Activating Token Index: 328

Text #9

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1320. Min Act: -0.0000

Data Index: 1775049 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1819017 (The Pile)

Max Activating Token Index: 376

Text #11

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1002. Min Act: -0.0000

Data Index: 912692 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.0920. Min Act: -0.0000

Data Index: 744740 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.0918. Min Act: -0.0000

Data Index: 965392 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1613172 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.0562. Min Act: -0.0000

Data Index: 765908 (The Pile)

Max Activating Token Index: 796

Text #16

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1814826 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.9817. Min Act: -0.0000

Data Index: 930295 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.0164. Min Act: -0.0000

Data Index: 300417 (The Pile)

Max Activating Token Index: 590

Text #19

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1286399 (The Pile)

Max Activating Token Index: 398