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

Dataset: The Pile

Neuron 1788 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: 0.7106. Min Range: -0.7106

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1604104 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.7076. Min Act: -0.0000

Data Index: 323807 (The Pile)

Max Activating Token Index: 770

Text #2

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6914. Min Act: -0.0000

Data Index: 79859 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6397. Min Act: -0.0000

Data Index: 206141 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1442687 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6569. Min Act: -0.0000

Data Index: 877777 (The Pile)

Max Activating Token Index: 531

Text #6

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1830920 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1016896 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1307076 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1535203 (The Pile)

Max Activating Token Index: 719

Text #10

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1691423 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6201. Min Act: -0.0000

Data Index: 167617 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6045. Min Act: -0.0000

Data Index: 118149 (The Pile)

Max Activating Token Index: 475

Text #13

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6211. Min Act: -0.0000

Data Index: 395521 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6016. Min Act: -0.0000

Data Index: 818535 (The Pile)

Max Activating Token Index: 605

Text #15

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1939088 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6189. Min Act: -0.0000

Data Index: 126694 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1451976 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1783096 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5582. Min Act: -0.0000

Data Index: 198970 (The Pile)

Max Activating Token Index: 614