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

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

Neuron 3228 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0927. Min Act: -0.0002

Data Index: 146744 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0841. Min Act: -0.0002

Data Index: 516633 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1337358 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1038650 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0779. Min Act: -0.0002

Data Index: 751884 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0800. Min Act: -0.0002

Data Index: 659310 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0783. Min Act: -0.0002

Data Index: 213908 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1152671 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0850. Min Act: -0.0002

Data Index: 696804 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0699. Min Act: -0.0002

Data Index: 471022 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1268623 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0691. Min Act: -0.0002

Data Index: 395327 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0921. Min Act: -0.0002

Data Index: 377672 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1542669 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0750. Min Act: -0.0002

Data Index: 335335 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1291596 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0640. Min Act: -0.0002

Data Index: 29691 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0760. Min Act: -0.0002

Data Index: 795340 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0707. Min Act: -0.0002

Data Index: 594519 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0739. Min Act: -0.0002

Data Index: 462988 (C4 (Web Text))

Max Activating Token Index: 640