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

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

Neuron 5782 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7547. Min Range: -2.7547

Max Act: 2.7547. Min Act: -0.0000

Data Index: 1374598 (Python Code)

Max Activating Token Index: 923

Text #1

Max Range: 2.7547. Min Range: -2.7547

Max Act: 2.0355. Min Act: -0.0000

Data Index: 1615022 (Python Code)

Max Activating Token Index: 171

Text #2

Max Range: 2.7547. Min Range: -2.7547

Max Act: 2.1897. Min Act: 0.0000

Data Index: 1473080 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 2.7547. Min Range: -2.7547

Max Act: 2.0057. Min Act: -0.0000

Data Index: 1427776 (Python Code)

Max Activating Token Index: 456

Text #4

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.9987. Min Act: -0.0000

Data Index: 1518840 (Python Code)

Max Activating Token Index: 90

Text #5

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.9080. Min Act: -0.0000

Data Index: 981042 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.8484. Min Act: -0.0000

Data Index: 1423306 (Python Code)

Max Activating Token Index: 845

Text #7

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.9799. Min Act: -0.0000

Data Index: 1534821 (Python Code)

Max Activating Token Index: 415

Text #8

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.8621. Min Act: -0.0000

Data Index: 848967 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.9090. Min Act: -0.0000

Data Index: 1403445 (Python Code)

Max Activating Token Index: 331

Text #10

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.7864. Min Act: -0.0000

Data Index: 1421091 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.8397. Min Act: -0.0000

Data Index: 1391267 (Python Code)

Max Activating Token Index: 608

Text #12

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.9982. Min Act: -0.0000

Data Index: 1643649 (Python Code)

Max Activating Token Index: 1013

Text #13

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.7584. Min Act: -0.0000

Data Index: 1546168 (Python Code)

Max Activating Token Index: 490

Text #14

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.8964. Min Act: -0.0000

Data Index: 1529208 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.6816. Min Act: -0.0000

Data Index: 1466581 (Python Code)

Max Activating Token Index: 831

Text #16

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.7712. Min Act: -0.0000

Data Index: 1421961 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.7525. Min Act: -0.0000

Data Index: 1474734 (Python Code)

Max Activating Token Index: 401

Text #18

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.7811. Min Act: -0.0000

Data Index: 1409346 (Python Code)

Max Activating Token Index: 462

Text #19

Max Range: 2.7547. Min Range: -2.7547

Max Act: 1.7870. Min Act: -0.0000

Data Index: 1500971 (Python Code)

Max Activating Token Index: 933