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

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

Neuron 1355 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3509. Min Range: -2.3509

Max Act: 2.3509. Min Act: -0.0000

Data Index: 802226 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 2.3509. Min Range: -2.3509

Max Act: 2.1792. Min Act: -0.0000

Data Index: 349689 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.8436. Min Act: -0.0000

Data Index: 70822 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.8751. Min Act: -0.0000

Data Index: 890508 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.9627. Min Act: -0.0000

Data Index: 569950 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.7077. Min Act: -0.0000

Data Index: 1031863 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.6940. Min Act: -0.0000

Data Index: 960109 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.6726. Min Act: -0.0000

Data Index: 961106 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.5902. Min Act: -0.0000

Data Index: 1188117 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.6696. Min Act: -0.0000

Data Index: 703356 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.7303. Min Act: -0.0000

Data Index: 1628571 (Python Code)

Max Activating Token Index: 297

Text #11

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.5882. Min Act: -0.0000

Data Index: 360729 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.5759. Min Act: -0.0000

Data Index: 41230 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.4895. Min Act: -0.0000

Data Index: 687267 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.5661. Min Act: -0.0000

Data Index: 41315 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.5048. Min Act: -0.0000

Data Index: 325066 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.3707. Min Act: -0.0000

Data Index: 806820 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.3617. Min Act: -0.0001

Data Index: 60123 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.4384. Min Act: -0.0000

Data Index: 116656 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 2.3509. Min Range: -2.3509

Max Act: 1.4168. Min Act: -0.0000

Data Index: 939544 (C4 (Web Text))

Max Activating Token Index: 603