Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3148 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.7851. Min Act: -0.0000

Data Index: 252404 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.5147. Min Act: -0.0000

Data Index: 154794 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.2370. Min Act: -0.0000

Data Index: 921195 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.1506. Min Act: -0.0000

Data Index: 628028 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.1002. Min Act: -0.0000

Data Index: 163037 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1003947 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 1.7851. Min Range: -1.7851

Max Act: 0.9894. Min Act: -0.0000

Data Index: 575 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1110344 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.0767. Min Act: -0.0000

Data Index: 530765 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 1.7851. Min Range: -1.7851

Max Act: 0.9558. Min Act: -0.0000

Data Index: 832303 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 1.7851. Min Range: -1.7851

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1157536 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 1.7851. Min Range: -1.7851

Max Act: 0.9640. Min Act: -0.0000

Data Index: 171146 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.0024. Min Act: -0.0000

Data Index: 985945 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 1.7851. Min Range: -1.7851

Max Act: 0.9302. Min Act: -0.0000

Data Index: 943793 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 1.7851. Min Range: -1.7851

Max Act: 0.9218. Min Act: -0.0000

Data Index: 364205 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 1.7851. Min Range: -1.7851

Max Act: 0.8979. Min Act: -0.0000

Data Index: 691968 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 1.7851. Min Range: -1.7851

Max Act: 0.8992. Min Act: -0.0000

Data Index: 788439 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 1.7851. Min Range: -1.7851

Max Act: 0.8340. Min Act: -0.0000

Data Index: 41423 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 1.7851. Min Range: -1.7851

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1182772 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 1.7851. Min Range: -1.7851

Max Act: 0.8334. Min Act: -0.0000

Data Index: 51587 (C4 (Web Text))

Max Activating Token Index: 289