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

Dataset: The Pile

Neuron 2256 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7154. Min Act: -0.0000

Data Index: 44777 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1176360 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7798. Min Act: -0.0000

Data Index: 452142 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7575. Min Act: -0.0000

Data Index: 227014 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1262145 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1537423 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7025. Min Act: -0.0000

Data Index: 181747 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7081. Min Act: 0.0000

Data Index: 234513 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7009. Min Act: -0.0000

Data Index: 720456 (The Pile)

Max Activating Token Index: 831

Text #9

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7170. Min Act: -0.0000

Data Index: 298719 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6747. Min Act: -0.0000

Data Index: 124733 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6317. Min Act: -0.0000

Data Index: 724286 (The Pile)

Max Activating Token Index: 742

Text #12

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1523893 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1759957 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1431669 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6590. Min Act: 0.0000

Data Index: 1227129 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1506907 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5955. Min Act: -0.0000

Data Index: 286433 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6421. Min Act: -0.0000

Data Index: 471606 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1730711 (The Pile)

Max Activating Token Index: 398