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

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

Neuron 2058 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1433795 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1623024 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1605057 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1607554 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2326. Min Act: -0.0000

Data Index: 45608 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2090. Min Act: -0.0000

Data Index: 633559 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1934. Min Act: -0.0000

Data Index: 1053374 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1505514 (Python Code)

Max Activating Token Index: 939

Text #8

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2072. Min Act: -0.0000

Data Index: 207729 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1795. Min Act: -0.0000

Data Index: 105367 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1826. Min Act: -0.0000

Data Index: 375840 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1654162 (Python Code)

Max Activating Token Index: 850

Text #12

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1932. Min Act: -0.0000

Data Index: 819547 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1489445 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1459017 (Python Code)

Max Activating Token Index: 662

Text #15

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1172854 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1571. Min Act: -0.0000

Data Index: 80350 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1656. Min Act: -0.0000

Data Index: 702586 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1662. Min Act: -0.0000

Data Index: 110022 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1602. Min Act: -0.0000

Data Index: 12371 (C4 (Web Text))

Max Activating Token Index: 317