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

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

Neuron 2800 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2250. Min Act: -0.0002

Data Index: 1251164 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2015. Min Act: -0.0002

Data Index: 1220059 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1945. Min Act: -0.0002

Data Index: 1036491 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1758. Min Act: -0.0002

Data Index: 1004985 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1878. Min Act: -0.0002

Data Index: 1138894 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1839. Min Act: -0.0002

Data Index: 843335 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1770. Min Act: -0.0002

Data Index: 12222 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1871. Min Act: -0.0002

Data Index: 1108499 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1739. Min Act: -0.0002

Data Index: 1178212 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1679. Min Act: -0.0002

Data Index: 290576 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1806. Min Act: -0.0002

Data Index: 665164 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1716. Min Act: -0.0002

Data Index: 836413 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1601. Min Act: -0.0002

Data Index: 544104 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1573. Min Act: -0.0002

Data Index: 321576 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1833. Min Act: -0.0002

Data Index: 544599 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1662. Min Act: -0.0002

Data Index: 1353600 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1957. Min Act: -0.0002

Data Index: 646624 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1453. Min Act: -0.0002

Data Index: 330113 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1558. Min Act: -0.0002

Data Index: 954859 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1460. Min Act: -0.0002

Data Index: 200884 (C4 (Web Text))

Max Activating Token Index: 680