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

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

Neuron 2437 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: 5.3623. Min Range: -5.3623

Max Act: 5.3623. Min Act: -0.0000

Data Index: 500028 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.1410. Min Act: -0.0000

Data Index: 33786 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 5.3623. Min Range: -5.3623

Max Act: 4.9023. Min Act: -0.0000

Data Index: 1142863 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 5.3623. Min Range: -5.3623

Max Act: 4.6901. Min Act: -0.0000

Data Index: 464384 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 5.3623. Min Range: -5.3623

Max Act: 4.2697. Min Act: -0.0000

Data Index: 995502 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 5.3623. Min Range: -5.3623

Max Act: 4.4366. Min Act: -0.0000

Data Index: 537843 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 5.3623. Min Range: -5.3623

Max Act: 4.4395. Min Act: -0.0000

Data Index: 495286 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 5.3623. Min Range: -5.3623

Max Act: 4.1816. Min Act: -0.0000

Data Index: 1253598 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 5.3623. Min Range: -5.3623

Max Act: 4.1548. Min Act: -0.0000

Data Index: 674652 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 5.3623. Min Range: -5.3623

Max Act: 4.2840. Min Act: -0.0000

Data Index: 640931 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 5.3623. Min Range: -5.3623

Max Act: 3.6850. Min Act: -0.0000

Data Index: 969813 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 5.3623. Min Range: -5.3623

Max Act: 3.8028. Min Act: -0.0000

Data Index: 304719 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 5.3623. Min Range: -5.3623

Max Act: 3.9549. Min Act: -0.0000

Data Index: 747372 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 5.3623. Min Range: -5.3623

Max Act: 4.0954. Min Act: -0.0000

Data Index: 301199 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 5.3623. Min Range: -5.3623

Max Act: 3.9057. Min Act: -0.0000

Data Index: 395840 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 5.3623. Min Range: -5.3623

Max Act: 3.8952. Min Act: -0.0000

Data Index: 277660 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 5.3623. Min Range: -5.3623

Max Act: 4.0417. Min Act: -0.0000

Data Index: 632405 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 5.3623. Min Range: -5.3623

Max Act: 3.8590. Min Act: -0.0000

Data Index: 283121 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 5.3623. Min Range: -5.3623

Max Act: 4.1729. Min Act: -0.0000

Data Index: 1493017 (Python Code)

Max Activating Token Index: 525

Text #19

Max Range: 5.3623. Min Range: -5.3623

Max Act: 3.7964. Min Act: -0.0000

Data Index: 148493 (C4 (Web Text))

Max Activating Token Index: 818