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

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

Neuron 3384 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.3855. Min Act: -0.0000

Data Index: 1567967 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.2864. Min Act: -0.0001

Data Index: 1632921 (Python Code)

Max Activating Token Index: 435

Text #2

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.2786. Min Act: -0.0001

Data Index: 1564707 (Python Code)

Max Activating Token Index: 158

Text #3

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.3617. Min Act: -0.0000

Data Index: 1477907 (Python Code)

Max Activating Token Index: 60

Text #4

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.1805. Min Act: -0.0001

Data Index: 1410907 (Python Code)

Max Activating Token Index: 769

Text #5

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.3090. Min Act: -0.0001

Data Index: 1614232 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.1439. Min Act: -0.0000

Data Index: 1608619 (Python Code)

Max Activating Token Index: 67

Text #7

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.2101. Min Act: -0.0001

Data Index: 1535760 (Python Code)

Max Activating Token Index: 700

Text #8

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.1236. Min Act: -0.0001

Data Index: 1399976 (Python Code)

Max Activating Token Index: 485

Text #9

Max Range: 2.3855. Min Range: -2.3855

Max Act: 1.8806. Min Act: -0.0000

Data Index: 1510888 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 2.3855. Min Range: -2.3855

Max Act: 1.9264. Min Act: -0.0000

Data Index: 1609200 (Python Code)

Max Activating Token Index: 154

Text #11

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.0562. Min Act: -0.0000

Data Index: 1486445 (Python Code)

Max Activating Token Index: 301

Text #12

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.1034. Min Act: -0.0000

Data Index: 1561255 (Python Code)

Max Activating Token Index: 69

Text #13

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.0814. Min Act: -0.0000

Data Index: 1470181 (Python Code)

Max Activating Token Index: 138

Text #14

Max Range: 2.3855. Min Range: -2.3855

Max Act: 1.9473. Min Act: -0.0000

Data Index: 1363253 (Python Code)

Max Activating Token Index: 633

Text #15

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.1937. Min Act: -0.0000

Data Index: 1527955 (Python Code)

Max Activating Token Index: 651

Text #16

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.2078. Min Act: -0.0000

Data Index: 1377585 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.1290. Min Act: -0.0000

Data Index: 1561556 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 2.3855. Min Range: -2.3855

Max Act: 2.0060. Min Act: -0.0000

Data Index: 1632045 (Python Code)

Max Activating Token Index: 756

Text #19

Max Range: 2.3855. Min Range: -2.3855

Max Act: 1.8037. Min Act: -0.0000

Data Index: 1577542 (Python Code)

Max Activating Token Index: 182