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

Dataset: The Pile

Neuron 1919 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.4456. Min Act: -0.0000

Data Index: 986797 (The Pile)

Max Activating Token Index: 603

Text #1

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.4387. Min Act: -0.0000

Data Index: 1709325 (The Pile)

Max Activating Token Index: 843

Text #2

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.2953. Min Act: -0.0000

Data Index: 844222 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1556013 (The Pile)

Max Activating Token Index: 893

Text #4

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.3831. Min Act: -0.0000

Data Index: 1664118 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1433846 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.2666. Min Act: -0.0000

Data Index: 1097462 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.2235. Min Act: -0.0000

Data Index: 672886 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1746. Min Act: -0.0000

Data Index: 101703 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1558965 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0533. Min Act: -0.0000

Data Index: 729771 (The Pile)

Max Activating Token Index: 977

Text #11

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1343. Min Act: -0.0000

Data Index: 716355 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1970. Min Act: -0.0000

Data Index: 478991 (The Pile)

Max Activating Token Index: 922

Text #13

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1067970 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0372. Min Act: -0.0000

Data Index: 750630 (The Pile)

Max Activating Token Index: 46

Text #15

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1713092 (The Pile)

Max Activating Token Index: 200

Text #16

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1309959 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0617. Min Act: -0.0000

Data Index: 997394 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0877. Min Act: -0.0000

Data Index: 396611 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0102. Min Act: -0.0000

Data Index: 702148 (The Pile)

Max Activating Token Index: 774