Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4076 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1759058 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.5199. Min Act: -0.0000

Data Index: 745372 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1695658 (The Pile)

Max Activating Token Index: 497

Text #3

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1810144 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1627689 (The Pile)

Max Activating Token Index: 307

Text #5

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1946533 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4069. Min Act: -0.0000

Data Index: 915679 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3963. Min Act: -0.0000

Data Index: 45780 (The Pile)

Max Activating Token Index: 418

Text #8

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1753241 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1493971 (The Pile)

Max Activating Token Index: 352

Text #10

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3808. Min Act: -0.0000

Data Index: 499839 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3667. Min Act: -0.0000

Data Index: 659237 (The Pile)

Max Activating Token Index: 356

Text #12

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1819500 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1190992 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1135421 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1161856 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3541. Min Act: -0.0000

Data Index: 328695 (The Pile)

Max Activating Token Index: 188

Text #17

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4046. Min Act: -0.0000

Data Index: 781152 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1954569 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1481463 (The Pile)

Max Activating Token Index: 599