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

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

Neuron 3696 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: 0.2689. Min Range: -0.2689

Max Act: 0.2657. Min Act: -0.0000

Data Index: 575441 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1130561 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1351405 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2157. Min Act: -0.0000

Data Index: 877889 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2006. Min Act: -0.0000

Data Index: 946597 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1235748 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1186120 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1210520 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1257307 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1944. Min Act: -0.0000

Data Index: 606145 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1903. Min Act: -0.0000

Data Index: 766994 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1865. Min Act: -0.0000

Data Index: 845365 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1894. Min Act: -0.0000

Data Index: 69319 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1674. Min Act: -0.0000

Data Index: 498856 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1748. Min Act: -0.0000

Data Index: 939599 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1270679 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1309040 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1779. Min Act: -0.0000

Data Index: 32720 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1573. Min Act: -0.0000

Data Index: 520241 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1676. Min Act: -0.0000

Data Index: 54763 (C4 (Web Text))

Max Activating Token Index: 224