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

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

Neuron 722 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2973. Min Range: -2.2973

Max Act: 2.2973. Min Act: -0.0000

Data Index: 642043 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.3228. Min Act: -0.0000

Data Index: 871478 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.2971. Min Act: -0.0000

Data Index: 551496 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.3287. Min Act: -0.0000

Data Index: 1120138 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.2942. Min Act: -0.0000

Data Index: 517006 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.2328. Min Act: -0.0000

Data Index: 1120826 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.2107. Min Act: -0.0000

Data Index: 1326215 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1222033 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.1347. Min Act: -0.0000

Data Index: 226530 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.2816. Min Act: -0.0000

Data Index: 973986 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.1832. Min Act: -0.0000

Data Index: 1303772 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.1892. Min Act: -0.0000

Data Index: 131066 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.1925. Min Act: -0.0000

Data Index: 85131 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.1725. Min Act: -0.0000

Data Index: 422992 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.2278. Min Act: -0.0000

Data Index: 199048 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.2076. Min Act: -0.0000

Data Index: 799785 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.0910. Min Act: -0.0000

Data Index: 694618 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1084136 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1026844 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 2.2973. Min Range: -2.2973

Max Act: 1.0863. Min Act: -0.0000

Data Index: 606065 (C4 (Web Text))

Max Activating Token Index: 439