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

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

Neuron 2362 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1645030 (Python Code)

Max Activating Token Index: 1012

Text #1

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8437. Min Act: -0.0000

Data Index: 43702 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7653. Min Act: -0.0000

Data Index: 715548 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1573738 (Python Code)

Max Activating Token Index: 350

Text #4

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8209. Min Act: 0.0001

Data Index: 1640036 (Python Code)

Max Activating Token Index: 504

Text #5

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7806. Min Act: -0.0000

Data Index: 522300 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1348862 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1551662 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1640861 (Python Code)

Max Activating Token Index: 848

Text #9

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1574729 (Python Code)

Max Activating Token Index: 624

Text #10

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1454342 (Python Code)

Max Activating Token Index: 407

Text #11

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1471386 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1536681 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1595046 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1404048 (Python Code)

Max Activating Token Index: 997

Text #15

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1416192 (Python Code)

Max Activating Token Index: 293

Text #16

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5701. Min Act: 0.0000

Data Index: 1591233 (Python Code)

Max Activating Token Index: 618

Text #17

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5678. Min Act: 0.0001

Data Index: 1393853 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1433193 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5412. Min Act: -0.0000

Data Index: 187750 (C4 (Web Text))

Max Activating Token Index: 307