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

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

Neuron 4933 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2238. Min Act: -0.0000

Data Index: 959052 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2273. Min Act: -0.0000

Data Index: 2694 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2033. Min Act: -0.0000

Data Index: 361091 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2070. Min Act: -0.0000

Data Index: 1128256 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2049. Min Act: -0.0000

Data Index: 900947 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1351914 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1259410 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1877. Min Act: -0.0000

Data Index: 741339 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1859. Min Act: -0.0000

Data Index: 193313 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1882. Min Act: -0.0000

Data Index: 567373 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1252111 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1819. Min Act: -0.0000

Data Index: 106520 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1792. Min Act: -0.0000

Data Index: 933762 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1780. Min Act: -0.0000

Data Index: 266545 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1698. Min Act: -0.0000

Data Index: 139691 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1816. Min Act: -0.0000

Data Index: 387066 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1691. Min Act: -0.0000

Data Index: 761090 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1736. Min Act: -0.0000

Data Index: 327945 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1720. Min Act: -0.0000

Data Index: 8651 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1606. Min Act: -0.0000

Data Index: 556084 (C4 (Web Text))

Max Activating Token Index: 696