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

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

Neuron 1603 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.7914. Min Act: -0.0000

Data Index: 1541506 (Python Code)

Max Activating Token Index: 818

Text #1

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.7318. Min Act: -0.0000

Data Index: 1407677 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.7169. Min Act: -0.0000

Data Index: 1647704 (Python Code)

Max Activating Token Index: 179

Text #3

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.7455. Min Act: -0.0000

Data Index: 1518935 (Python Code)

Max Activating Token Index: 1013

Text #4

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5536. Min Act: -0.0000

Data Index: 1636026 (Python Code)

Max Activating Token Index: 109

Text #5

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5594. Min Act: -0.0000

Data Index: 1633361 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5393. Min Act: -0.0000

Data Index: 1422200 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5015. Min Act: -0.0000

Data Index: 1554425 (Python Code)

Max Activating Token Index: 67

Text #8

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1649436 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.3824. Min Act: -0.0000

Data Index: 1423504 (Python Code)

Max Activating Token Index: 635

Text #10

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4079. Min Act: -0.0000

Data Index: 1585142 (Python Code)

Max Activating Token Index: 984

Text #11

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.3674. Min Act: -0.0000

Data Index: 1569931 (Python Code)

Max Activating Token Index: 772

Text #12

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.3509. Min Act: -0.0000

Data Index: 1643000 (Python Code)

Max Activating Token Index: 992

Text #13

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4200. Min Act: -0.0000

Data Index: 1362162 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.2862. Min Act: -0.0000

Data Index: 1568951 (Python Code)

Max Activating Token Index: 875

Text #15

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.2615. Min Act: -0.0000

Data Index: 1402474 (Python Code)

Max Activating Token Index: 856

Text #16

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1634297 (Python Code)

Max Activating Token Index: 80

Text #17

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.2820. Min Act: -0.0000

Data Index: 1595038 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1482369 (Python Code)

Max Activating Token Index: 707

Text #19

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1362714 (Python Code)

Max Activating Token Index: 819