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

Dataset: The Pile

Neuron 630 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2556. Min Range: -5.2556

Max Act: 5.2556. Min Act: -0.0000

Data Index: 1477989 (The Pile)

Max Activating Token Index: 376

Text #1

Max Range: 5.2556. Min Range: -5.2556

Max Act: 4.7026. Min Act: -0.0000

Data Index: 1300193 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 5.2556. Min Range: -5.2556

Max Act: 4.3331. Min Act: -0.0000

Data Index: 578948 (The Pile)

Max Activating Token Index: 195

Text #3

Max Range: 5.2556. Min Range: -5.2556

Max Act: 4.4071. Min Act: -0.0000

Data Index: 1400837 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 5.2556. Min Range: -5.2556

Max Act: 3.5192. Min Act: -0.0000

Data Index: 860878 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 5.2556. Min Range: -5.2556

Max Act: 3.7640. Min Act: -0.0000

Data Index: 1232291 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 5.2556. Min Range: -5.2556

Max Act: 4.0901. Min Act: -0.0000

Data Index: 1429222 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 5.2556. Min Range: -5.2556

Max Act: 4.2266. Min Act: -0.0000

Data Index: 1749103 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 5.2556. Min Range: -5.2556

Max Act: 3.7257. Min Act: -0.0000

Data Index: 101305 (The Pile)

Max Activating Token Index: 499

Text #9

Max Range: 5.2556. Min Range: -5.2556

Max Act: 3.4936. Min Act: -0.0000

Data Index: 1170684 (The Pile)

Max Activating Token Index: 746

Text #10

Max Range: 5.2556. Min Range: -5.2556

Max Act: 4.0718. Min Act: -0.0000

Data Index: 1410487 (The Pile)

Max Activating Token Index: 605

Text #11

Max Range: 5.2556. Min Range: -5.2556

Max Act: 3.7619. Min Act: -0.0000

Data Index: 1336837 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 5.2556. Min Range: -5.2556

Max Act: 4.2586. Min Act: -0.0000

Data Index: 1366906 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 5.2556. Min Range: -5.2556

Max Act: 3.9417. Min Act: -0.0000

Data Index: 1712541 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 5.2556. Min Range: -5.2556

Max Act: 3.8579. Min Act: -0.0000

Data Index: 1255565 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 5.2556. Min Range: -5.2556

Max Act: 3.8594. Min Act: -0.0000

Data Index: 776542 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 5.2556. Min Range: -5.2556

Max Act: 4.1845. Min Act: -0.0000

Data Index: 951767 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 5.2556. Min Range: -5.2556

Max Act: 4.0097. Min Act: -0.0000

Data Index: 1956874 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 5.2556. Min Range: -5.2556

Max Act: 3.9525. Min Act: -0.0000

Data Index: 1837798 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 5.2556. Min Range: -5.2556

Max Act: 3.7740. Min Act: -0.0000

Data Index: 1957755 (The Pile)

Max Activating Token Index: 328