Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 219 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2725. Min Range: -2.2725

Max Act: 2.2725. Min Act: -0.0000

Data Index: 190609 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.6368. Min Act: -0.0000

Data Index: 615977 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.6068. Min Act: -0.0000

Data Index: 784019 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.4388. Min Act: -0.0000

Data Index: 943283 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.4694. Min Act: -0.0000

Data Index: 894824 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.4222. Min Act: -0.0000

Data Index: 54691 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.4070. Min Act: -0.0000

Data Index: 311719 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.4987. Min Act: -0.0000

Data Index: 152279 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.4632. Min Act: -0.0000

Data Index: 71584 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.3658. Min Act: -0.0000

Data Index: 1324559 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.3424. Min Act: -0.0000

Data Index: 727573 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.2815. Min Act: -0.0000

Data Index: 926951 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.3164. Min Act: -0.0000

Data Index: 92951 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.2350. Min Act: -0.0000

Data Index: 1266124 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.2376. Min Act: -0.0000

Data Index: 292042 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.2871. Min Act: -0.0000

Data Index: 250959 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1147774 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.1019. Min Act: -0.0000

Data Index: 111893 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.2235. Min Act: -0.0000

Data Index: 984636 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 2.2725. Min Range: -2.2725

Max Act: 1.1569. Min Act: -0.0000

Data Index: 474426 (C4 (Web Text))

Max Activating Token Index: 951