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

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

Neuron 3037 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: 2.2914. Min Range: -2.2914

Max Act: 2.1901. Min Act: -0.0000

Data Index: 578462 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 2.2914. Min Range: -2.2914

Max Act: 2.2914. Min Act: -0.0000

Data Index: 1039820 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.9814. Min Act: -0.0000

Data Index: 708139 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.7414. Min Act: -0.0000

Data Index: 831614 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.9568. Min Act: -0.0000

Data Index: 820150 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.8711. Min Act: -0.0000

Data Index: 456915 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.7722. Min Act: -0.0000

Data Index: 353045 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.7582. Min Act: -0.0000

Data Index: 646722 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.8564. Min Act: -0.0000

Data Index: 986908 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.6573. Min Act: -0.0000

Data Index: 999845 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.8438. Min Act: -0.0000

Data Index: 1280412 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.7554. Min Act: -0.0000

Data Index: 669236 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.7426. Min Act: -0.0000

Data Index: 701032 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.7376. Min Act: -0.0000

Data Index: 1234013 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.7084. Min Act: -0.0000

Data Index: 573848 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.6576. Min Act: -0.0000

Data Index: 211340 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.6696. Min Act: -0.0000

Data Index: 217310 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.7073. Min Act: -0.0000

Data Index: 1358582 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.5829. Min Act: -0.0000

Data Index: 1207854 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 2.2914. Min Range: -2.2914

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1198524 (C4 (Web Text))

Max Activating Token Index: 622