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

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

Neuron 424 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.7064. Min Act: -0.0000

Data Index: 306491 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.7660. Min Act: -0.0000

Data Index: 136986 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.4589. Min Act: -0.0000

Data Index: 1149638 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.5490. Min Act: -0.0000

Data Index: 417227 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.4442. Min Act: -0.0000

Data Index: 1042918 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.4273. Min Act: -0.0000

Data Index: 1283480 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.7267. Min Act: -0.0000

Data Index: 1322852 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.3982. Min Act: -0.0000

Data Index: 408145 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.1233. Min Act: -0.0000

Data Index: 782445 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.2111. Min Act: -0.0000

Data Index: 72083 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.2023. Min Act: 0.0003

Data Index: 144015 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.1961. Min Act: -0.0000

Data Index: 1193274 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.2009. Min Act: -0.0000

Data Index: 903525 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.2933. Min Act: -0.0000

Data Index: 1172102 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.2826. Min Act: -0.0000

Data Index: 937776 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.2169. Min Act: -0.0000

Data Index: 1512843 (Python Code)

Max Activating Token Index: 605

Text #16

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.3110. Min Act: -0.0000

Data Index: 231822 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.1812. Min Act: -0.0000

Data Index: 1133770 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.1714. Min Act: -0.0000

Data Index: 129740 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 2.7660. Min Range: -2.7660

Max Act: 2.0567. Min Act: -0.0000

Data Index: 713801 (C4 (Web Text))

Max Activating Token Index: 777