Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 860 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1437871 (Python Code)

Max Activating Token Index: 624

Text #1

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1534809 (Python Code)

Max Activating Token Index: 687

Text #2

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1491165 (Python Code)

Max Activating Token Index: 493

Text #3

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1772. Min Act: -0.0001

Data Index: 1426546 (Python Code)

Max Activating Token Index: 892

Text #4

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1772. Min Act: -0.0000

Data Index: 40652 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1450581 (Python Code)

Max Activating Token Index: 764

Text #6

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1762. Min Act: -0.0001

Data Index: 1609992 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1788. Min Act: -0.0001

Data Index: 1358487 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1651423 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1548757 (Python Code)

Max Activating Token Index: 718

Text #10

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1486237 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1408940 (Python Code)

Max Activating Token Index: 504

Text #12

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1382352 (Python Code)

Max Activating Token Index: 962

Text #13

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1524548 (Python Code)

Max Activating Token Index: 548

Text #14

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1454639 (Python Code)

Max Activating Token Index: 801

Text #15

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1630078 (Python Code)

Max Activating Token Index: 336

Text #16

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1562489 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1656140 (Python Code)

Max Activating Token Index: 76

Text #18

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1513181 (Python Code)

Max Activating Token Index: 289

Text #19

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1656594 (Python Code)

Max Activating Token Index: 919