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

Dataset: The Pile

Neuron 1553 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1058083 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.8264. Min Act: -0.0000

Data Index: 191838 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.7503. Min Act: 0.0000

Data Index: 1343978 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1497948 (The Pile)

Max Activating Token Index: 461

Text #4

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.6626. Min Act: 0.0000

Data Index: 333561 (The Pile)

Max Activating Token Index: 578

Text #5

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.6756. Min Act: -0.0000

Data Index: 287088 (The Pile)

Max Activating Token Index: 98

Text #6

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1051465 (The Pile)

Max Activating Token Index: 107

Text #7

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5885. Min Act: -0.0000

Data Index: 417763 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1021447 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1390111 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5450. Min Act: 0.0000

Data Index: 1277718 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5265. Min Act: -0.0000

Data Index: 851508 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5231. Min Act: -0.0000

Data Index: 459136 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5516. Min Act: -0.0000

Data Index: 678830 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1805201 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1109481 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5293. Min Act: 0.0000

Data Index: 1917341 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5303. Min Act: -0.0000

Data Index: 109966 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5404. Min Act: -0.0000

Data Index: 1505231 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.4884. Min Act: -0.0000

Data Index: 147817 (The Pile)

Max Activating Token Index: 389