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

Dataset: The Pile

Neuron 683 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.4245. Min Act: -0.0000

Data Index: 585268 (The Pile)

Max Activating Token Index: 184

Text #1

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1555846 (The Pile)

Max Activating Token Index: 424

Text #2

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.1440. Min Act: -0.0000

Data Index: 634076 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1360336 (The Pile)

Max Activating Token Index: 778

Text #4

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.1011. Min Act: -0.0000

Data Index: 1628222 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0963. Min Act: -0.0000

Data Index: 377867 (The Pile)

Max Activating Token Index: 72

Text #6

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0282. Min Act: -0.0000

Data Index: 311084 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0712. Min Act: -0.0000

Data Index: 858750 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1182235 (The Pile)

Max Activating Token Index: 327

Text #9

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.1399. Min Act: -0.0000

Data Index: 374978 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1041347 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0302. Min Act: -0.0000

Data Index: 109008 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0103. Min Act: -0.0000

Data Index: 889421 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1660062 (The Pile)

Max Activating Token Index: 948

Text #14

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0118. Min Act: -0.0000

Data Index: 601534 (The Pile)

Max Activating Token Index: 323

Text #15

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0631. Min Act: -0.0000

Data Index: 1933439 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 1.4245. Min Range: -1.4245

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1997039 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 1.4245. Min Range: -1.4245

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1588370 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 1.4245. Min Range: -1.4245

Max Act: 0.9820. Min Act: -0.0000

Data Index: 174370 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 1.4245. Min Range: -1.4245

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1018362 (The Pile)

Max Activating Token Index: 429