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

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

Neuron 3674 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2215. Min Act: -0.0002

Data Index: 3891 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1876. Min Act: -0.0002

Data Index: 1268196 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1986. Min Act: -0.0002

Data Index: 261063 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2027. Min Act: -0.0002

Data Index: 1014037 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1943. Min Act: -0.0001

Data Index: 506400 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1953. Min Act: -0.0002

Data Index: 1041239 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2048. Min Act: -0.0002

Data Index: 535281 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1836. Min Act: -0.0002

Data Index: 1303110 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1894. Min Act: -0.0002

Data Index: 111691 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2007. Min Act: -0.0002

Data Index: 17291 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1799. Min Act: -0.0002

Data Index: 1115043 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1886. Min Act: -0.0002

Data Index: 107027 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2008. Min Act: -0.0002

Data Index: 585030 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1307538 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1893. Min Act: -0.0002

Data Index: 285141 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2011. Min Act: -0.0002

Data Index: 964038 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1986. Min Act: -0.0002

Data Index: 890140 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1851. Min Act: -0.0002

Data Index: 750501 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1901. Min Act: -0.0002

Data Index: 5178 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1767. Min Act: -0.0001

Data Index: 902248 (C4 (Web Text))

Max Activating Token Index: 183