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

Dataset: The Pile

Neuron 3880 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.2940. Min Act: -0.0000

Data Index: 783778 (The Pile)

Max Activating Token Index: 555

Text #1

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.2624. Min Act: -0.0000

Data Index: 353828 (The Pile)

Max Activating Token Index: 691

Text #2

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.1988. Min Act: -0.0000

Data Index: 493556 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.2185. Min Act: -0.0000

Data Index: 60752 (The Pile)

Max Activating Token Index: 851

Text #4

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0639. Min Act: -0.0000

Data Index: 1219094 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.1083. Min Act: -0.0000

Data Index: 115972 (The Pile)

Max Activating Token Index: 777

Text #6

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.1770. Min Act: -0.0000

Data Index: 159076 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0426. Min Act: -0.0000

Data Index: 540100 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0467. Min Act: -0.0000

Data Index: 1055515 (The Pile)

Max Activating Token Index: 655

Text #9

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1064762 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1438342 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0343. Min Act: -0.0000

Data Index: 503718 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9468. Min Act: -0.0000

Data Index: 378501 (The Pile)

Max Activating Token Index: 550

Text #13

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1098139 (The Pile)

Max Activating Token Index: 901

Text #14

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0154. Min Act: -0.0000

Data Index: 320492 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1437701 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0395. Min Act: -0.0000

Data Index: 1773050 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9458. Min Act: -0.0000

Data Index: 1465815 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.1793. Min Act: -0.0000

Data Index: 1120848 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1108598 (The Pile)

Max Activating Token Index: 260