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

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

Neuron 6104 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3816. Min Range: -1.3816

Max Act: 1.3816. Min Act: -0.0000

Data Index: 1591571 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1402986 (Python Code)

Max Activating Token Index: 386

Text #2

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1650701 (Python Code)

Max Activating Token Index: 357

Text #3

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1562042 (Python Code)

Max Activating Token Index: 179

Text #4

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1560415 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1585916 (Python Code)

Max Activating Token Index: 391

Text #6

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1438078 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1495234 (Python Code)

Max Activating Token Index: 605

Text #8

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1365565 (Python Code)

Max Activating Token Index: 646

Text #9

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1614414 (Python Code)

Max Activating Token Index: 578

Text #10

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.6128. Min Act: -0.0000

Data Index: 18715 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1394299 (Python Code)

Max Activating Token Index: 571

Text #12

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1524603 (Python Code)

Max Activating Token Index: 952

Text #13

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.6461. Min Act: -0.0000

Data Index: 518582 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.6259. Min Act: -0.0000

Data Index: 151599 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1081601 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.6741. Min Act: -0.0000

Data Index: 30095 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.6728. Min Act: -0.0000

Data Index: 994966 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1440180 (Python Code)

Max Activating Token Index: 222

Text #19

Max Range: 1.3816. Min Range: -1.3816

Max Act: 0.6385. Min Act: -0.0000

Data Index: 107917 (C4 (Web Text))

Max Activating Token Index: 964