Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3625 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.9313. Min Act: -0.0001

Data Index: 393562 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.9017. Min Act: -0.0001

Data Index: 233916 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8441. Min Act: -0.0001

Data Index: 1136009 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8895. Min Act: -0.0001

Data Index: 935877 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8377. Min Act: -0.0001

Data Index: 575765 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7966. Min Act: -0.0001

Data Index: 178863 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8325. Min Act: -0.0001

Data Index: 1000836 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7830. Min Act: -0.0001

Data Index: 1242009 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8051. Min Act: -0.0001

Data Index: 765736 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8032. Min Act: -0.0001

Data Index: 118165 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7679. Min Act: -0.0001

Data Index: 356398 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8120. Min Act: -0.0001

Data Index: 1298367 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7343. Min Act: -0.0001

Data Index: 888111 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7753. Min Act: -0.0001

Data Index: 215612 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7352. Min Act: -0.0001

Data Index: 316025 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7303. Min Act: -0.0001

Data Index: 280746 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7050. Min Act: -0.0001

Data Index: 809540 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7005. Min Act: -0.0001

Data Index: 1345455 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7725. Min Act: -0.0001

Data Index: 939494 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7480. Min Act: -0.0001

Data Index: 582533 (C4 (Web Text))

Max Activating Token Index: 623