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

Dataset: The Pile

Neuron 3293 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1773. Min Act: -0.0000

Data Index: 637756 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1377897 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1592998 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1531157 (The Pile)

Max Activating Token Index: 746

Text #4

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1170. Min Act: -0.0000

Data Index: 390659 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1161592 (The Pile)

Max Activating Token Index: 553

Text #6

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1953572 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1319707 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1081637 (The Pile)

Max Activating Token Index: 151

Text #9

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1023. Min Act: -0.0000

Data Index: 212345 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1781217 (The Pile)

Max Activating Token Index: 555

Text #11

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1752559 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1109. Min Act: -0.0000

Data Index: 871022 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.0975. Min Act: -0.0000

Data Index: 916083 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.0910. Min Act: -0.0000

Data Index: 871852 (The Pile)

Max Activating Token Index: 865

Text #15

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.0976. Min Act: -0.0000

Data Index: 43176 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.0962. Min Act: -0.0000

Data Index: 1706702 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1910512 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1180822 (The Pile)

Max Activating Token Index: 107

Text #19

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.0921. Min Act: -0.0000

Data Index: 673557 (The Pile)

Max Activating Token Index: 339