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

Dataset: The Pile

Neuron 1364 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: 1.1876. Min Range: -1.1876

Max Act: 1.1876. Min Act: -0.0000

Data Index: 1734545 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.1040. Min Act: -0.0000

Data Index: 372235 (The Pile)

Max Activating Token Index: 512

Text #2

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1637142 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1484994 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8391. Min Act: -0.0000

Data Index: 983218 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1400105 (The Pile)

Max Activating Token Index: 171

Text #6

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1979461 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7593. Min Act: -0.0000

Data Index: 388907 (The Pile)

Max Activating Token Index: 870

Text #8

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1610853 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1077161 (The Pile)

Max Activating Token Index: 719

Text #10

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7169. Min Act: -0.0000

Data Index: 639872 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.6644. Min Act: -0.0000

Data Index: 869679 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1657984 (The Pile)

Max Activating Token Index: 790

Text #13

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7008. Min Act: -0.0000

Data Index: 801760 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1117903 (The Pile)

Max Activating Token Index: 44

Text #15

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.6581. Min Act: -0.0000

Data Index: 293339 (The Pile)

Max Activating Token Index: 438

Text #16

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1958866 (The Pile)

Max Activating Token Index: 776

Text #17

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.6146. Min Act: 0.0000

Data Index: 100718 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1370178 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1454128 (The Pile)

Max Activating Token Index: 1015