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

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

Neuron 1898 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1621758 (Python Code)

Max Activating Token Index: 282

Text #1

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1650111 (Python Code)

Max Activating Token Index: 848

Text #2

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1602115 (Python Code)

Max Activating Token Index: 1017

Text #3

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.8325. Min Act: -0.0000

Data Index: 746335 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1412360 (Python Code)

Max Activating Token Index: 889

Text #5

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1188906 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1587596 (Python Code)

Max Activating Token Index: 449

Text #7

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1508476 (Python Code)

Max Activating Token Index: 56

Text #8

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1583568 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1383923 (Python Code)

Max Activating Token Index: 456

Text #10

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1594304 (Python Code)

Max Activating Token Index: 268

Text #11

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1651089 (Python Code)

Max Activating Token Index: 434

Text #12

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1606691 (Python Code)

Max Activating Token Index: 330

Text #13

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1643788 (Python Code)

Max Activating Token Index: 454

Text #14

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1518698 (Python Code)

Max Activating Token Index: 737

Text #15

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1611731 (Python Code)

Max Activating Token Index: 306

Text #16

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1416820 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1525877 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1477156 (Python Code)

Max Activating Token Index: 282

Text #19

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6765. Min Act: -0.0000

Data Index: 918983 (C4 (Web Text))

Max Activating Token Index: 159