Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 839 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1869. Min Act: -0.0002

Data Index: 1013943 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1881. Min Act: -0.0002

Data Index: 1310983 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1867. Min Act: -0.0002

Data Index: 556615 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1853. Min Act: -0.0002

Data Index: 1154496 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1834. Min Act: -0.0002

Data Index: 136602 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1861. Min Act: -0.0002

Data Index: 874024 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1758. Min Act: -0.0002

Data Index: 157702 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1805. Min Act: -0.0002

Data Index: 225260 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1804. Min Act: -0.0002

Data Index: 1109559 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1817. Min Act: -0.0002

Data Index: 534526 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1799. Min Act: -0.0002

Data Index: 226059 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1736. Min Act: -0.0002

Data Index: 634213 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1783. Min Act: -0.0002

Data Index: 582829 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1673. Min Act: -0.0002

Data Index: 950577 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1747. Min Act: -0.0002

Data Index: 170445 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1705. Min Act: -0.0002

Data Index: 467054 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1755. Min Act: -0.0002

Data Index: 676028 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1553. Min Act: -0.0002

Data Index: 1081136 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1628. Min Act: -0.0002

Data Index: 243209 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1641. Min Act: -0.0002

Data Index: 977958 (C4 (Web Text))

Max Activating Token Index: 520