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

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

Neuron 319 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1302655 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6973. Min Act: -0.0000

Data Index: 601402 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6460. Min Act: -0.0000

Data Index: 914038 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6354. Min Act: -0.0000

Data Index: 755137 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1268560 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5875. Min Act: -0.0000

Data Index: 337643 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1295037 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5895. Min Act: -0.0000

Data Index: 847942 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1236204 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1040820 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5262. Min Act: -0.0000

Data Index: 446334 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1339734 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5347. Min Act: -0.0000

Data Index: 161371 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5345. Min Act: -0.0000

Data Index: 674521 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1155733 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.4897. Min Act: -0.0000

Data Index: 778844 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1166287 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.4977. Min Act: -0.0000

Data Index: 514027 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5151. Min Act: -0.0000

Data Index: 179336 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5136. Min Act: -0.0000

Data Index: 987289 (C4 (Web Text))

Max Activating Token Index: 336