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

Dataset: The Pile

Neuron 4878 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: 0.8961. Min Range: -0.8961

Max Act: 0.8961. Min Act: -0.0000

Data Index: 99730 (The Pile)

Max Activating Token Index: 407

Text #1

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1607666 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7540. Min Act: -0.0000

Data Index: 290595 (The Pile)

Max Activating Token Index: 131

Text #3

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8659. Min Act: -0.0000

Data Index: 496518 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1315354 (The Pile)

Max Activating Token Index: 222

Text #5

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7594. Min Act: -0.0000

Data Index: 13507 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8360. Min Act: -0.0000

Data Index: 406813 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7448. Min Act: -0.0000

Data Index: 1329673 (The Pile)

Max Activating Token Index: 168

Text #8

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1917389 (The Pile)

Max Activating Token Index: 607

Text #9

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7047. Min Act: -0.0000

Data Index: 107824 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1484619 (The Pile)

Max Activating Token Index: 459

Text #11

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1005831 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8634. Min Act: -0.0000

Data Index: 726781 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1781694 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5716. Min Act: -0.0000

Data Index: 189446 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5168. Min Act: -0.0000

Data Index: 762580 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1615336 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.4170. Min Act: -0.0000

Data Index: 694053 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.4355. Min Act: -0.0000

Data Index: 176902 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1271173 (The Pile)

Max Activating Token Index: 924