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

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

Neuron 1296 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: 1.0767. Min Range: -1.0767

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1456236 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8393. Min Act: -0.0000

Data Index: 786327 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6876. Min Act: -0.0000

Data Index: 74162 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1290953 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.7425. Min Act: -0.0000

Data Index: 524423 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6681. Min Act: -0.0000

Data Index: 883039 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6742. Min Act: -0.0000

Data Index: 960663 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6353. Min Act: -0.0000

Data Index: 591412 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1587030 (Python Code)

Max Activating Token Index: 935

Text #9

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1637599 (Python Code)

Max Activating Token Index: 67

Text #10

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1629769 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6886. Min Act: -0.0000

Data Index: 271590 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5886. Min Act: -0.0000

Data Index: 484102 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5974. Min Act: -0.0000

Data Index: 673788 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1225128 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5800. Min Act: -0.0000

Data Index: 137808 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6109. Min Act: -0.0000

Data Index: 29956 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1578923 (Python Code)

Max Activating Token Index: 424

Text #18

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6432. Min Act: -0.0000

Data Index: 743000 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6290. Min Act: -0.0000

Data Index: 279522 (C4 (Web Text))

Max Activating Token Index: 138