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

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

Neuron 3061 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: 0.6695. Min Range: -0.6695

Max Act: 0.6695. Min Act: -0.0000

Data Index: 77138 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1040265 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1298381 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.6013. Min Act: -0.0000

Data Index: 944440 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5252. Min Act: -0.0000

Data Index: 146874 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5337. Min Act: -0.0000

Data Index: 710917 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4883. Min Act: -0.0000

Data Index: 992834 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5015. Min Act: -0.0000

Data Index: 473512 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1213546 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1158200 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4913. Min Act: -0.0000

Data Index: 503004 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1328418 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4688. Min Act: -0.0000

Data Index: 684754 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4709. Min Act: -0.0000

Data Index: 330685 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4674. Min Act: -0.0000

Data Index: 268793 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4630. Min Act: -0.0000

Data Index: 509760 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4757. Min Act: -0.0000

Data Index: 524271 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4733. Min Act: -0.0000

Data Index: 502946 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1072544 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4982. Min Act: -0.0000

Data Index: 458902 (C4 (Web Text))

Max Activating Token Index: 763