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

Dataset: The Pile

Neuron 4357 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: 0.1799. Min Range: -0.1799

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1682868 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1858020 (The Pile)

Max Activating Token Index: 850

Text #2

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1862388 (The Pile)

Max Activating Token Index: 806

Text #3

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1496. Min Act: -0.0000

Data Index: 826764 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1301007 (The Pile)

Max Activating Token Index: 959

Text #5

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1623897 (The Pile)

Max Activating Token Index: 890

Text #6

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1978781 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1419. Min Act: -0.0000

Data Index: 444744 (The Pile)

Max Activating Token Index: 963

Text #8

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1152. Min Act: -0.0000

Data Index: 319378 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1500657 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1061672 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1250032 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1185. Min Act: -0.0000

Data Index: 975556 (The Pile)

Max Activating Token Index: 975

Text #13

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1493448 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1041577 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1455792 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0859. Min Act: -0.0000

Data Index: 461083 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0888. Min Act: -0.0000

Data Index: 542610 (The Pile)

Max Activating Token Index: 991

Text #18

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0964. Min Act: -0.0000

Data Index: 632611 (The Pile)

Max Activating Token Index: 938

Text #19

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1395768 (The Pile)

Max Activating Token Index: 840