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

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

Neuron 3335 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2136. Min Act: -0.0002

Data Index: 711422 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2065. Min Act: -0.0002

Data Index: 616280 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1874. Min Act: -0.0002

Data Index: 655783 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2493. Min Act: -0.0002

Data Index: 580398 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2320. Min Act: -0.0002

Data Index: 722670 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2283. Min Act: -0.0002

Data Index: 1066451 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2172. Min Act: -0.0002

Data Index: 1013691 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2325. Min Act: -0.0002

Data Index: 225072 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1953. Min Act: -0.0002

Data Index: 132860 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2017. Min Act: -0.0002

Data Index: 546875 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1938. Min Act: -0.0002

Data Index: 1148800 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1915. Min Act: -0.0002

Data Index: 64871 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2053. Min Act: -0.0002

Data Index: 1099130 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1728. Min Act: -0.0002

Data Index: 931130 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1786. Min Act: -0.0002

Data Index: 1224438 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1829. Min Act: -0.0002

Data Index: 1117237 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1904. Min Act: -0.0002

Data Index: 667029 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2007. Min Act: -0.0002

Data Index: 177975 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2143. Min Act: -0.0002

Data Index: 444933 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1890. Min Act: -0.0002

Data Index: 962901 (C4 (Web Text))

Max Activating Token Index: 284