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

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

Neuron 2304 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2361. Min Act: -0.0001

Data Index: 88424 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2092. Min Act: -0.0001

Data Index: 1137691 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1058392 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2050. Min Act: -0.0001

Data Index: 861001 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1903. Min Act: -0.0001

Data Index: 207202 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1894. Min Act: -0.0001

Data Index: 567907 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1884. Min Act: -0.0001

Data Index: 742520 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1944. Min Act: -0.0001

Data Index: 730830 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1223130 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1913. Min Act: -0.0001

Data Index: 701693 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1914. Min Act: -0.0001

Data Index: 376871 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1127138 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1876. Min Act: -0.0001

Data Index: 1113626 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1804. Min Act: -0.0001

Data Index: 978632 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1812. Min Act: -0.0001

Data Index: 1188926 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1780. Min Act: -0.0001

Data Index: 428823 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1851. Min Act: -0.0001

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1905. Min Act: -0.0001

Data Index: 64222 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1837. Min Act: -0.0001

Data Index: 533744 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1820. Min Act: -0.0001

Data Index: 963954 (C4 (Web Text))

Max Activating Token Index: 888