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

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

Neuron 1991 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: 2.4117. Min Range: -2.4117

Max Act: 2.4117. Min Act: -0.0000

Data Index: 1480036 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.3821. Min Act: -0.0000

Data Index: 1557772 (Python Code)

Max Activating Token Index: 69

Text #2

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.1487. Min Act: -0.0000

Data Index: 1385971 (Python Code)

Max Activating Token Index: 142

Text #3

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.1901. Min Act: -0.0000

Data Index: 1569552 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.2765. Min Act: -0.0000

Data Index: 1644925 (Python Code)

Max Activating Token Index: 926

Text #5

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.0883. Min Act: -0.0000

Data Index: 1641743 (Python Code)

Max Activating Token Index: 149

Text #6

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.0757. Min Act: -0.0000

Data Index: 1485898 (Python Code)

Max Activating Token Index: 694

Text #7

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.0926. Min Act: -0.0000

Data Index: 1615954 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.0874. Min Act: -0.0000

Data Index: 1437644 (Python Code)

Max Activating Token Index: 980

Text #9

Max Range: 2.4117. Min Range: -2.4117

Max Act: 1.9615. Min Act: -0.0000

Data Index: 1523833 (Python Code)

Max Activating Token Index: 641

Text #10

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.0578. Min Act: -0.0000

Data Index: 1489406 (Python Code)

Max Activating Token Index: 114

Text #11

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.1645. Min Act: -0.0000

Data Index: 1391247 (Python Code)

Max Activating Token Index: 657

Text #12

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.0641. Min Act: -0.0000

Data Index: 1391025 (Python Code)

Max Activating Token Index: 567

Text #13

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.0425. Min Act: -0.0000

Data Index: 1463101 (Python Code)

Max Activating Token Index: 601

Text #14

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.0448. Min Act: -0.0000

Data Index: 1472283 (Python Code)

Max Activating Token Index: 977

Text #15

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.1582. Min Act: -0.0000

Data Index: 1512948 (Python Code)

Max Activating Token Index: 372

Text #16

Max Range: 2.4117. Min Range: -2.4117

Max Act: 1.9245. Min Act: -0.0000

Data Index: 409629 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 2.4117. Min Range: -2.4117

Max Act: 2.0258. Min Act: -0.0000

Data Index: 1631746 (Python Code)

Max Activating Token Index: 520

Text #18

Max Range: 2.4117. Min Range: -2.4117

Max Act: 1.9980. Min Act: -0.0000

Data Index: 1498807 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 2.4117. Min Range: -2.4117

Max Act: 1.9904. Min Act: -0.0000

Data Index: 1558391 (Python Code)

Max Activating Token Index: 831