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

Dataset: The Pile

Neuron 809 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0658. Min Range: -1.0658

Max Act: 1.0658. Min Act: -0.0000

Data Index: 151474 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9063. Min Act: -0.0000

Data Index: 925172 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9048. Min Act: -0.0000

Data Index: 819805 (The Pile)

Max Activating Token Index: 64

Text #3

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1162015 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1516134 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1215597 (The Pile)

Max Activating Token Index: 454

Text #6

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7698. Min Act: -0.0000

Data Index: 393569 (The Pile)

Max Activating Token Index: 826

Text #7

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7323. Min Act: -0.0000

Data Index: 956968 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7665. Min Act: -0.0000

Data Index: 270057 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1841999 (The Pile)

Max Activating Token Index: 556

Text #10

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1301965 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.6642. Min Act: -0.0000

Data Index: 501753 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1856666 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7057. Min Act: -0.0000

Data Index: 946196 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7247. Min Act: -0.0000

Data Index: 483261 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1040725 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.6231. Min Act: -0.0000

Data Index: 877435 (The Pile)

Max Activating Token Index: 119

Text #17

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8074. Min Act: -0.0000

Data Index: 992962 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7549. Min Act: -0.0000

Data Index: 385518 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.6561. Min Act: -0.0000

Data Index: 903405 (The Pile)

Max Activating Token Index: 120