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

Dataset: The Pile

Neuron 1484 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1631177 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1909975 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1652738 (The Pile)

Max Activating Token Index: 883

Text #3

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6854. Min Act: -0.0000

Data Index: 105360 (The Pile)

Max Activating Token Index: 97

Text #4

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6699. Min Act: -0.0000

Data Index: 336573 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6502. Min Act: -0.0000

Data Index: 618333 (The Pile)

Max Activating Token Index: 285

Text #6

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6636. Min Act: -0.0000

Data Index: 38645 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6249. Min Act: -0.0000

Data Index: 108173 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5933. Min Act: -0.0000

Data Index: 709781 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1930075 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5977. Min Act: -0.0000

Data Index: 506398 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1655611 (The Pile)

Max Activating Token Index: 445

Text #12

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5735. Min Act: -0.0000

Data Index: 59227 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5835. Min Act: -0.0000

Data Index: 564183 (The Pile)

Max Activating Token Index: 898

Text #14

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1641627 (The Pile)

Max Activating Token Index: 1005

Text #15

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5741. Min Act: -0.0000

Data Index: 694916 (The Pile)

Max Activating Token Index: 438

Text #16

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5652. Min Act: 0.0000

Data Index: 335981 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5658. Min Act: -0.0000

Data Index: 633826 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1881269 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1597722 (The Pile)

Max Activating Token Index: 69