Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1953 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0711. Min Act: -0.0005

Data Index: 387364 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0005

Data Index: 36139 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0613. Min Act: -0.0005

Data Index: 1121330 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0648. Min Act: -0.0005

Data Index: 1229090 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0616. Min Act: -0.0005

Data Index: 913035 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0601. Min Act: -0.0005

Data Index: 685704 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0610. Min Act: -0.0005

Data Index: 439027 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0666. Min Act: -0.0005

Data Index: 367428 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0609. Min Act: -0.0005

Data Index: 544481 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0598. Min Act: -0.0005

Data Index: 1138285 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0633. Min Act: -0.0005

Data Index: 1271900 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0580. Min Act: -0.0005

Data Index: 465428 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0557. Min Act: -0.0005

Data Index: 631495 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0557. Min Act: -0.0005

Data Index: 485563 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0545. Min Act: -0.0005

Data Index: 384322 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0546. Min Act: -0.0005

Data Index: 1332782 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0528. Min Act: -0.0005

Data Index: 1107661 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0525. Min Act: -0.0005

Data Index: 612337 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0485. Min Act: -0.0005

Data Index: 747159 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0521. Min Act: -0.0005

Data Index: 1111954 (C4 (Web Text))

Max Activating Token Index: 1022