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

Dataset: The Pile

Neuron 3325 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: 5.4716. Min Range: -5.4716

Max Act: 5.4716. Min Act: -0.0000

Data Index: 244505 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 5.4716. Min Range: -5.4716

Max Act: 4.5468. Min Act: -0.0000

Data Index: 1056361 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 5.4716. Min Range: -5.4716

Max Act: 4.6618. Min Act: -0.0000

Data Index: 1703779 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 5.4716. Min Range: -5.4716

Max Act: 4.4306. Min Act: -0.0000

Data Index: 1011796 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 5.4716. Min Range: -5.4716

Max Act: 4.1005. Min Act: -0.0000

Data Index: 1881549 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 5.4716. Min Range: -5.4716

Max Act: 4.3847. Min Act: -0.0000

Data Index: 983305 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 5.4716. Min Range: -5.4716

Max Act: 4.6843. Min Act: -0.0000

Data Index: 305598 (The Pile)

Max Activating Token Index: 167

Text #7

Max Range: 5.4716. Min Range: -5.4716

Max Act: 4.2773. Min Act: -0.0000

Data Index: 882380 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 5.4716. Min Range: -5.4716

Max Act: 4.1092. Min Act: -0.0000

Data Index: 592568 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 5.4716. Min Range: -5.4716

Max Act: 3.9045. Min Act: -0.0000

Data Index: 1332837 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 5.4716. Min Range: -5.4716

Max Act: 3.8429. Min Act: -0.0000

Data Index: 562505 (The Pile)

Max Activating Token Index: 130

Text #11

Max Range: 5.4716. Min Range: -5.4716

Max Act: 3.6031. Min Act: -0.0000

Data Index: 502025 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 5.4716. Min Range: -5.4716

Max Act: 3.3744. Min Act: -0.0000

Data Index: 1487724 (The Pile)

Max Activating Token Index: 600

Text #13

Max Range: 5.4716. Min Range: -5.4716

Max Act: 3.6929. Min Act: -0.0000

Data Index: 271256 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 5.4716. Min Range: -5.4716

Max Act: 3.5531. Min Act: -0.0000

Data Index: 1289536 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 5.4716. Min Range: -5.4716

Max Act: 3.3780. Min Act: -0.0000

Data Index: 1493881 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 5.4716. Min Range: -5.4716

Max Act: 3.5025. Min Act: -0.0000

Data Index: 1177852 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 5.4716. Min Range: -5.4716

Max Act: 3.5077. Min Act: -0.0000

Data Index: 1031623 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 5.4716. Min Range: -5.4716

Max Act: 3.2857. Min Act: -0.0000

Data Index: 974100 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 5.4716. Min Range: -5.4716

Max Act: 3.2504. Min Act: -0.0000

Data Index: 1991470 (The Pile)

Max Activating Token Index: 167