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

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

Neuron 3516 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: 1.7789. Min Range: -1.7789

Max Act: 1.7789. Min Act: -0.0000

Data Index: 1589321 (Python Code)

Max Activating Token Index: 655

Text #1

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.7258. Min Act: -0.0000

Data Index: 384201 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.6736. Min Act: -0.0000

Data Index: 1537850 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.6619. Min Act: -0.0000

Data Index: 1454710 (Python Code)

Max Activating Token Index: 363

Text #4

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.5672. Min Act: -0.0000

Data Index: 1535842 (Python Code)

Max Activating Token Index: 585

Text #5

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.5969. Min Act: -0.0000

Data Index: 1625220 (Python Code)

Max Activating Token Index: 223

Text #6

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.6163. Min Act: -0.0000

Data Index: 754366 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.6344. Min Act: -0.0000

Data Index: 1091758 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.6800. Min Act: -0.0000

Data Index: 1623031 (Python Code)

Max Activating Token Index: 675

Text #9

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.4639. Min Act: -0.0000

Data Index: 253221 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.4024. Min Act: -0.0000

Data Index: 453364 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.4127. Min Act: -0.0000

Data Index: 1369563 (Python Code)

Max Activating Token Index: 832

Text #12

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.3620. Min Act: -0.0000

Data Index: 1039354 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.3818. Min Act: -0.0000

Data Index: 1505009 (Python Code)

Max Activating Token Index: 58

Text #14

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.4259. Min Act: -0.0000

Data Index: 238571 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.2477. Min Act: -0.0000

Data Index: 418902 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.3927. Min Act: -0.0000

Data Index: 1542375 (Python Code)

Max Activating Token Index: 791

Text #17

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.3400. Min Act: -0.0000

Data Index: 1090442 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.3449. Min Act: -0.0000

Data Index: 1653955 (Python Code)

Max Activating Token Index: 245

Text #19

Max Range: 1.7789. Min Range: -1.7789

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1352919 (C4 (Web Text))

Max Activating Token Index: 278