Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3082 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1804921 (The Pile)

Max Activating Token Index: 931

Text #1

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1559032 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5266. Min Act: -0.0000

Data Index: 918505 (The Pile)

Max Activating Token Index: 871

Text #3

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6375. Min Act: -0.0000

Data Index: 385403 (The Pile)

Max Activating Token Index: 709

Text #4

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5274. Min Act: -0.0000

Data Index: 638404 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1229691 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1271043 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1530363 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1850927 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1808546 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1716161 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6739. Min Act: -0.0000

Data Index: 771715 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5428. Min Act: -0.0000

Data Index: 147313 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1218197 (The Pile)

Max Activating Token Index: 981

Text #14

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1691725 (The Pile)

Max Activating Token Index: 943

Text #15

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5806. Min Act: -0.0000

Data Index: 286275 (The Pile)

Max Activating Token Index: 862

Text #16

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1615766 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5302. Min Act: -0.0000

Data Index: 417410 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1064547 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1920757 (The Pile)

Max Activating Token Index: 812