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

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

Neuron 6070 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.2824. Min Act: -0.0000

Data Index: 1609918 (Python Code)

Max Activating Token Index: 358

Text #1

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1522240 (Python Code)

Max Activating Token Index: 961

Text #2

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9707. Min Act: -0.0000

Data Index: 1402973 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.0876. Min Act: -0.0000

Data Index: 1535773 (Python Code)

Max Activating Token Index: 560

Text #4

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1628313 (Python Code)

Max Activating Token Index: 834

Text #5

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1515699 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1602827 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9224. Min Act: -0.0000

Data Index: 1398221 (Python Code)

Max Activating Token Index: 480

Text #8

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1527794 (Python Code)

Max Activating Token Index: 753

Text #9

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1654622 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1625256 (Python Code)

Max Activating Token Index: 83

Text #11

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1583924 (Python Code)

Max Activating Token Index: 287

Text #12

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1565047 (Python Code)

Max Activating Token Index: 322

Text #13

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1473106 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1416050 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8004. Min Act: -0.0000

Data Index: 1589272 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1383694 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1422598 (Python Code)

Max Activating Token Index: 235

Text #18

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1605639 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1610022 (Python Code)

Max Activating Token Index: 1018