Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2397 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.2260. Min Act: -0.0000

Data Index: 604474 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.2200. Min Act: -0.0000

Data Index: 143457 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.2051. Min Act: -0.0000

Data Index: 301329 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.2064. Min Act: -0.0000

Data Index: 582492 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.2105. Min Act: -0.0000

Data Index: 928395 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1971. Min Act: -0.0001

Data Index: 413225 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1067769 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1890. Min Act: -0.0000

Data Index: 856547 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1826. Min Act: -0.0000

Data Index: 93975 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1819. Min Act: -0.0001

Data Index: 527998 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1812. Min Act: -0.0000

Data Index: 834981 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1688. Min Act: -0.0001

Data Index: 692874 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1490790 (Python Code)

Max Activating Token Index: 589

Text #13

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1367295 (Python Code)

Max Activating Token Index: 827

Text #14

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1797. Min Act: -0.0000

Data Index: 627192 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1770. Min Act: -0.0000

Data Index: 134815 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1036170 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1703. Min Act: -0.0001

Data Index: 398733 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1706. Min Act: -0.0001

Data Index: 695384 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1490650 (Python Code)

Max Activating Token Index: 487