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

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

Neuron 2104 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.7517. Min Act: -0.0000

Data Index: 978803 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.7399. Min Act: -0.0000

Data Index: 504392 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6818. Min Act: -0.0000

Data Index: 359586 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.7110. Min Act: -0.0000

Data Index: 456704 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.7283. Min Act: -0.0000

Data Index: 318240 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.7233. Min Act: -0.0000

Data Index: 705390 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6371. Min Act: -0.0000

Data Index: 737200 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5640. Min Act: -0.0000

Data Index: 716887 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5181. Min Act: -0.0000

Data Index: 271829 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.4673. Min Act: -0.0000

Data Index: 174485 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5181. Min Act: -0.0000

Data Index: 510011 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5338. Min Act: -0.0000

Data Index: 331309 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5149. Min Act: -0.0000

Data Index: 522194 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1238021 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.4672. Min Act: -0.0000

Data Index: 394620 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1246942 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1274591 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1061504 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5144. Min Act: -0.0000

Data Index: 809 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5387. Min Act: -0.0000

Data Index: 774660 (C4 (Web Text))

Max Activating Token Index: 792