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

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

Neuron 609 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9397. Min Range: -4.9397

Max Act: 4.9397. Min Act: -0.0000

Data Index: 1110907 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 4.9397. Min Range: -4.9397

Max Act: 3.4177. Min Act: -0.0000

Data Index: 348409 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 4.9397. Min Range: -4.9397

Max Act: 3.4380. Min Act: -0.0000

Data Index: 126389 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 4.9397. Min Range: -4.9397

Max Act: 3.2706. Min Act: -0.0000

Data Index: 913345 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 4.9397. Min Range: -4.9397

Max Act: 3.5013. Min Act: -0.0000

Data Index: 52827 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 4.9397. Min Range: -4.9397

Max Act: 3.3373. Min Act: -0.0000

Data Index: 859142 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 4.9397. Min Range: -4.9397

Max Act: 3.1313. Min Act: -0.0000

Data Index: 1188433 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 4.9397. Min Range: -4.9397

Max Act: 3.0509. Min Act: -0.0000

Data Index: 286082 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 4.9397. Min Range: -4.9397

Max Act: 3.0911. Min Act: -0.0000

Data Index: 1275534 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 4.9397. Min Range: -4.9397

Max Act: 2.9088. Min Act: -0.0000

Data Index: 573045 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 4.9397. Min Range: -4.9397

Max Act: 2.8338. Min Act: -0.0000

Data Index: 1035102 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 4.9397. Min Range: -4.9397

Max Act: 2.7400. Min Act: -0.0000

Data Index: 643614 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 4.9397. Min Range: -4.9397

Max Act: 2.5552. Min Act: -0.0000

Data Index: 162163 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 4.9397. Min Range: -4.9397

Max Act: 2.6592. Min Act: -0.0000

Data Index: 1352261 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 4.9397. Min Range: -4.9397

Max Act: 2.5513. Min Act: -0.0000

Data Index: 633322 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 4.9397. Min Range: -4.9397

Max Act: 2.5791. Min Act: -0.0000

Data Index: 1059414 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 4.9397. Min Range: -4.9397

Max Act: 2.5751. Min Act: -0.0000

Data Index: 1156621 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 4.9397. Min Range: -4.9397

Max Act: 2.4485. Min Act: -0.0000

Data Index: 557963 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 4.9397. Min Range: -4.9397

Max Act: 2.6718. Min Act: -0.0000

Data Index: 125093 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 4.9397. Min Range: -4.9397

Max Act: 2.5274. Min Act: -0.0000

Data Index: 987752 (C4 (Web Text))

Max Activating Token Index: 419