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

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

Neuron 5237 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.9329. Min Act: -0.0000

Data Index: 1536027 (Python Code)

Max Activating Token Index: 646

Text #1

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1541701 (Python Code)

Max Activating Token Index: 285

Text #2

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.7460. Min Act: -0.0000

Data Index: 1403994 (Python Code)

Max Activating Token Index: 621

Text #3

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.8262. Min Act: -0.0000

Data Index: 1264055 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.6890. Min Act: -0.0000

Data Index: 395808 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.7175. Min Act: -0.0000

Data Index: 33442 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.7082. Min Act: -0.0000

Data Index: 1429122 (Python Code)

Max Activating Token Index: 224

Text #7

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.5077. Min Act: -0.0000

Data Index: 22982 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.6293. Min Act: -0.0000

Data Index: 380221 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.7365. Min Act: -0.0000

Data Index: 1468180 (Python Code)

Max Activating Token Index: 268

Text #10

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.6016. Min Act: -0.0000

Data Index: 1412353 (Python Code)

Max Activating Token Index: 824

Text #11

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.5904. Min Act: -0.0000

Data Index: 1138431 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.4846. Min Act: -0.0000

Data Index: 1633289 (Python Code)

Max Activating Token Index: 150

Text #13

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.5132. Min Act: -0.0000

Data Index: 1448542 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.6714. Min Act: -0.0000

Data Index: 735582 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.5626. Min Act: -0.0000

Data Index: 1650559 (Python Code)

Max Activating Token Index: 109

Text #16

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.5557. Min Act: -0.0000

Data Index: 1516079 (Python Code)

Max Activating Token Index: 95

Text #17

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.5478. Min Act: -0.0000

Data Index: 1402731 (Python Code)

Max Activating Token Index: 118

Text #18

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.4483. Min Act: -0.0000

Data Index: 1417851 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 1.9329. Min Range: -1.9329

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1373404 (Python Code)

Max Activating Token Index: 963