Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3138 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1611607 (Python Code)

Max Activating Token Index: 94

Text #1

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.2053. Min Act: -0.0000

Data Index: 677519 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1975. Min Act: 0.0000

Data Index: 910837 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.2042. Min Act: -0.0000

Data Index: 717045 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.2022. Min Act: -0.0000

Data Index: 832736 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1976. Min Act: -0.0000

Data Index: 350163 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1300774 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1927. Min Act: 0.0002

Data Index: 14056 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1650688 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1859. Min Act: -0.0000

Data Index: 775010 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1927. Min Act: -0.0000

Data Index: 793785 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1884. Min Act: -0.0000

Data Index: 181168 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1681. Min Act: -0.0000

Data Index: 426702 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1660. Min Act: -0.0000

Data Index: 769859 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1834. Min Act: -0.0000

Data Index: 266129 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1296171 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1707. Min Act: -0.0000

Data Index: 193142 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1806. Min Act: -0.0000

Data Index: 941792 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1680. Min Act: -0.0000

Data Index: 392966 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1709. Min Act: -0.0000

Data Index: 363141 (C4 (Web Text))

Max Activating Token Index: 192