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

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

Neuron 2327 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: 6.2265. Min Range: -6.2265

Max Act: 6.2265. Min Act: -0.0000

Data Index: 807259 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 6.2265. Min Range: -6.2265

Max Act: 6.1366. Min Act: -0.0000

Data Index: 1326386 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 6.2265. Min Range: -6.2265

Max Act: 6.1304. Min Act: -0.0000

Data Index: 265988 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 6.2265. Min Range: -6.2265

Max Act: 6.0695. Min Act: -0.0000

Data Index: 1279463 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.9789. Min Act: -0.0000

Data Index: 143388 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.7465. Min Act: -0.0000

Data Index: 584565 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.7101. Min Act: -0.0000

Data Index: 1089389 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 6.2265. Min Range: -6.2265

Max Act: 6.0622. Min Act: -0.0000

Data Index: 254219 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.8134. Min Act: -0.0000

Data Index: 1067817 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.6076. Min Act: -0.0000

Data Index: 727923 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.9535. Min Act: -0.0000

Data Index: 663849 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.7495. Min Act: -0.0000

Data Index: 1204509 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.6948. Min Act: -0.0000

Data Index: 987849 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.4837. Min Act: -0.0000

Data Index: 152128 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.6208. Min Act: -0.0000

Data Index: 344400 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.7729. Min Act: -0.0000

Data Index: 1254401 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.3646. Min Act: -0.0000

Data Index: 165206 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.5601. Min Act: -0.0000

Data Index: 258308 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.5500. Min Act: -0.0000

Data Index: 568938 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 6.2265. Min Range: -6.2265

Max Act: 5.5376. Min Act: -0.0000

Data Index: 1187696 (C4 (Web Text))

Max Activating Token Index: 215