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

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

Neuron 4486 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: 0.2244. Min Range: -0.2244

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1507034 (Python Code)

Max Activating Token Index: 925

Text #1

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1084881 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1515272 (Python Code)

Max Activating Token Index: 315

Text #3

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1859. Min Act: -0.0000

Data Index: 535705 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.2056. Min Act: 0.0000

Data Index: 1287361 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.2109. Min Act: -0.0000

Data Index: 884546 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1408034 (Python Code)

Max Activating Token Index: 180

Text #7

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1995. Min Act: -0.0000

Data Index: 423123 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1906. Min Act: -0.0000

Data Index: 290736 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1978. Min Act: -0.0000

Data Index: 642445 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.2242. Min Act: -0.0000

Data Index: 131099 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1222150 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1571820 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1805. Min Act: -0.0000

Data Index: 477157 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1536912 (Python Code)

Max Activating Token Index: 411

Text #15

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1735. Min Act: -0.0000

Data Index: 275448 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1116186 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1588842 (Python Code)

Max Activating Token Index: 492

Text #18

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1534. Min Act: -0.0000

Data Index: 752285 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1702. Min Act: -0.0000

Data Index: 365929 (C4 (Web Text))

Max Activating Token Index: 672