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

Dataset: The Pile

Neuron 947 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: 5.5009. Min Range: -5.5009

Max Act: 5.5009. Min Act: -0.0000

Data Index: 246679 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 5.5009. Min Range: -5.5009

Max Act: 5.4186. Min Act: -0.0000

Data Index: 1780894 (The Pile)

Max Activating Token Index: 889

Text #2

Max Range: 5.5009. Min Range: -5.5009

Max Act: 5.1407. Min Act: -0.0000

Data Index: 1734647 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 5.5009. Min Range: -5.5009

Max Act: 5.0141. Min Act: -0.0000

Data Index: 823566 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 5.5009. Min Range: -5.5009

Max Act: 4.9605. Min Act: -0.0000

Data Index: 1803809 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 5.5009. Min Range: -5.5009

Max Act: 4.6441. Min Act: -0.0000

Data Index: 1911466 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 5.5009. Min Range: -5.5009

Max Act: 4.4079. Min Act: -0.0000

Data Index: 958155 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 5.5009. Min Range: -5.5009

Max Act: 4.3556. Min Act: -0.0000

Data Index: 1798300 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.4063. Min Act: -0.0000

Data Index: 1361840 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.4505. Min Act: -0.0000

Data Index: 1453596 (The Pile)

Max Activating Token Index: 692

Text #10

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.3851. Min Act: -0.0000

Data Index: 260517 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.2434. Min Act: -0.0000

Data Index: 1792480 (The Pile)

Max Activating Token Index: 708

Text #12

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.5008. Min Act: -0.0000

Data Index: 1552529 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.3160. Min Act: -0.0000

Data Index: 831031 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.2619. Min Act: -0.0000

Data Index: 90608 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.0879. Min Act: -0.0000

Data Index: 1543168 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.4135. Min Act: -0.0000

Data Index: 1161976 (The Pile)

Max Activating Token Index: 627

Text #17

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.0631. Min Act: -0.0000

Data Index: 912190 (The Pile)

Max Activating Token Index: 517

Text #18

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.2184. Min Act: -0.0000

Data Index: 1499909 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 5.5009. Min Range: -5.5009

Max Act: 3.2150. Min Act: -0.0000

Data Index: 1060796 (The Pile)

Max Activating Token Index: 586