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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3175 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0696. Min Range: -1.0696

Max Act: 1.0696. Min Act: -0.0000

Data Index: 1076256 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.8251. Min Act: -0.0000

Data Index: 503746 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1282947 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1150054 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.7929. Min Act: -0.0000

Data Index: 533160 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1355522 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.7722. Min Act: -0.0000

Data Index: 669214 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.7781. Min Act: -0.0000

Data Index: 206951 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1270741 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1302537 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.7331. Min Act: -0.0000

Data Index: 739698 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.6773. Min Act: -0.0000

Data Index: 754273 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.6992. Min Act: -0.0000

Data Index: 979457 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.7247. Min Act: -0.0000

Data Index: 732879 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.6704. Min Act: 0.0001

Data Index: 578904 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1127392 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.6830. Min Act: -0.0000

Data Index: 496783 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.6665. Min Act: 0.0002

Data Index: 856110 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.6777. Min Act: -0.0000

Data Index: 559332 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.6830. Min Act: 0.0002

Data Index: 882840 (C4 (Web Text))

Max Activating Token Index: 93