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

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

Neuron 681 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: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0002

Data Index: 286516 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0610. Min Act: -0.0002

Data Index: 926261 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1287625 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0532. Min Act: -0.0002

Data Index: 252956 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0529. Min Act: -0.0002

Data Index: 284026 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0407. Min Act: -0.0002

Data Index: 563753 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0439. Min Act: -0.0002

Data Index: 886611 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0433. Min Act: -0.0002

Data Index: 264515 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0444. Min Act: -0.0002

Data Index: 346501 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0513. Min Act: -0.0002

Data Index: 723993 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0503. Min Act: -0.0002

Data Index: 18292 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0442. Min Act: -0.0002

Data Index: 38635 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0441. Min Act: -0.0002

Data Index: 257519 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0438. Min Act: -0.0003

Data Index: 964345 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0455. Min Act: -0.0002

Data Index: 988904 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0377. Min Act: -0.0002

Data Index: 311481 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0354. Min Act: -0.0002

Data Index: 533513 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0410. Min Act: -0.0002

Data Index: 35214 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0445. Min Act: -0.0002

Data Index: 482902 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0430. Min Act: -0.0002

Data Index: 137187 (C4 (Web Text))

Max Activating Token Index: 64