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

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

Neuron 1988 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: 0.2307. Min Range: -0.2307

Max Act: 0.2307. Min Act: -0.0000

Data Index: 462476 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2120. Min Act: -0.0001

Data Index: 414941 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2128. Min Act: -0.0001

Data Index: 818950 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1638657 (Python Code)

Max Activating Token Index: 557

Text #4

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1904. Min Act: -0.0000

Data Index: 543204 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1890. Min Act: -0.0001

Data Index: 269765 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1595049 (Python Code)

Max Activating Token Index: 901

Text #7

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1873. Min Act: -0.0001

Data Index: 1390553 (Python Code)

Max Activating Token Index: 958

Text #8

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1457598 (Python Code)

Max Activating Token Index: 445

Text #9

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1870. Min Act: -0.0001

Data Index: 1606870 (Python Code)

Max Activating Token Index: 416

Text #10

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1448343 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1528273 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1819. Min Act: -0.0000

Data Index: 827954 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1816. Min Act: -0.0000

Data Index: 892297 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1947. Min Act: -0.0001

Data Index: 1366801 (Python Code)

Max Activating Token Index: 708

Text #15

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1473786 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1283773 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1356750 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1609. Min Act: -0.0000

Data Index: 855622 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1465574 (Python Code)

Max Activating Token Index: 105