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

Dataset: The Pile

Neuron 1641 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1232961 (The Pile)

Max Activating Token Index: 494

Text #1

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5797. Min Act: -0.0000

Data Index: 234398 (The Pile)

Max Activating Token Index: 289

Text #2

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5330. Min Act: -0.0000

Data Index: 308673 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5871. Min Act: -0.0000

Data Index: 920645 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5431. Min Act: -0.0000

Data Index: 61394 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1098198 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1014260 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5713. Min Act: -0.0000

Data Index: 773997 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1431490 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4677. Min Act: -0.0000

Data Index: 27174 (The Pile)

Max Activating Token Index: 294

Text #10

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1173349 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4746. Min Act: -0.0000

Data Index: 82480 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1077354 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1933354 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1630079 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4445. Min Act: -0.0000

Data Index: 518403 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1239903 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4255. Min Act: -0.0000

Data Index: 851899 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4166. Min Act: -0.0000

Data Index: 727007 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4217. Min Act: -0.0000

Data Index: 93953 (The Pile)

Max Activating Token Index: 464