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

Dataset: The Pile

Neuron 839 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: 0.6163. Min Range: -0.6163

Max Act: 0.6163. Min Act: -0.0000

Data Index: 671658 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5724. Min Act: -0.0000

Data Index: 265093 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1184301 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1425244 (The Pile)

Max Activating Token Index: 583

Text #4

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1491464 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1833678 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1346580 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1550031 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4702. Min Act: -0.0000

Data Index: 717857 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4965. Min Act: -0.0000

Data Index: 530903 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4985. Min Act: 0.0000

Data Index: 1085794 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1194977 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4731. Min Act: -0.0000

Data Index: 313408 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4916. Min Act: 0.0000

Data Index: 1704069 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4716. Min Act: 0.0000

Data Index: 468934 (The Pile)

Max Activating Token Index: 866

Text #15

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4714. Min Act: 0.0000

Data Index: 1238551 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4697. Min Act: -0.0000

Data Index: 319654 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4645. Min Act: -0.0000

Data Index: 479633 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4478. Min Act: -0.0000

Data Index: 837786 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1592639 (The Pile)

Max Activating Token Index: 716