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

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

Neuron 2251 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.5534. Min Act: -0.0000

Data Index: 41643 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.3834. Min Act: -0.0000

Data Index: 295356 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.3792. Min Act: -0.0000

Data Index: 1197801 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.3075. Min Act: -0.0000

Data Index: 705837 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.3053. Min Act: -0.0000

Data Index: 1018073 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.2059. Min Act: -0.0000

Data Index: 354040 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.1514. Min Act: -0.0000

Data Index: 17833 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.1779. Min Act: -0.0000

Data Index: 163018 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1287182 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.1339. Min Act: -0.0000

Data Index: 1103986 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.1401. Min Act: -0.0000

Data Index: 823531 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.1860. Min Act: -0.0000

Data Index: 286306 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1102829 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.1245. Min Act: -0.0000

Data Index: 833214 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.0782. Min Act: -0.0000

Data Index: 1015443 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.0692. Min Act: -0.0000

Data Index: 810192 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.0318. Min Act: -0.0000

Data Index: 402190 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.0030. Min Act: -0.0000

Data Index: 582830 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.0026. Min Act: -0.0000

Data Index: 1222781 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.5534. Min Range: -1.5534

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1035178 (C4 (Web Text))

Max Activating Token Index: 87