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

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

Neuron 2994 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1121655 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2247. Min Act: -0.0000

Data Index: 491768 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2127. Min Act: -0.0001

Data Index: 165856 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2015. Min Act: -0.0000

Data Index: 724454 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1840. Min Act: -0.0000

Data Index: 236159 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1901. Min Act: -0.0000

Data Index: 95901 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1049061 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1833. Min Act: -0.0000

Data Index: 148049 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1773. Min Act: -0.0001

Data Index: 628617 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1300911 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1697. Min Act: -0.0000

Data Index: 650196 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1122899 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1740. Min Act: -0.0000

Data Index: 979701 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1804. Min Act: -0.0001

Data Index: 1042793 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1279223 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1761. Min Act: -0.0001

Data Index: 1104844 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1730. Min Act: -0.0000

Data Index: 600485 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1653. Min Act: -0.0000

Data Index: 15312 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1723. Min Act: -0.0000

Data Index: 663737 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1661. Min Act: -0.0000

Data Index: 391454 (C4 (Web Text))

Max Activating Token Index: 65