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

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

Neuron 2916 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1098587 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.5320. Min Act: -0.0000

Data Index: 547936 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.5129. Min Act: -0.0000

Data Index: 736807 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.5226. Min Act: -0.0000

Data Index: 601548 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4957. Min Act: -0.0000

Data Index: 250926 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4756. Min Act: -0.0000

Data Index: 969600 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.5047. Min Act: -0.0000

Data Index: 915741 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4860. Min Act: -0.0000

Data Index: 309831 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4837. Min Act: -0.0000

Data Index: 269066 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4864. Min Act: -0.0000

Data Index: 705592 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1124021 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.5091. Min Act: -0.0000

Data Index: 318886 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4700. Min Act: -0.0000

Data Index: 745050 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4548. Min Act: -0.0000

Data Index: 578759 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4838. Min Act: -0.0000

Data Index: 884556 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4364. Min Act: -0.0000

Data Index: 325646 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4628. Min Act: -0.0000

Data Index: 635841 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4473. Min Act: -0.0000

Data Index: 314837 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4492. Min Act: -0.0000

Data Index: 488595 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.5741. Min Range: -0.5741

Max Act: 0.4427. Min Act: -0.0000

Data Index: 90794 (C4 (Web Text))

Max Activating Token Index: 439