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

Dataset: The Pile

Neuron 1851 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1765002 (The Pile)

Max Activating Token Index: 543

Text #1

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1717948 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5168. Min Act: -0.0000

Data Index: 718345 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5726. Min Act: -0.0000

Data Index: 219874 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1734940 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5141. Min Act: -0.0000

Data Index: 56507 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5201. Min Act: -0.0000

Data Index: 3341 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1180826 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4810. Min Act: -0.0000

Data Index: 415082 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4929. Min Act: -0.0000

Data Index: 197321 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5042. Min Act: -0.0000

Data Index: 963658 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4390. Min Act: -0.0000

Data Index: 196083 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4711. Min Act: -0.0000

Data Index: 344683 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1662876 (The Pile)

Max Activating Token Index: 364

Text #14

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1073801 (The Pile)

Max Activating Token Index: 781

Text #15

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1608907 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4701. Min Act: -0.0000

Data Index: 865358 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4525. Min Act: -0.0000

Data Index: 603539 (The Pile)

Max Activating Token Index: 452

Text #18

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1242660 (The Pile)

Max Activating Token Index: 627

Text #19

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1335662 (The Pile)

Max Activating Token Index: 90