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

Dataset: The Pile

Neuron 4932 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0139. Min Act: -0.0000

Data Index: 916562 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0133. Min Act: -0.0000

Data Index: 521 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0129. Min Act: -0.0000

Data Index: 1397846 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0124. Min Act: -0.0000

Data Index: 1661750 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0123. Min Act: 0.0000

Data Index: 509909 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0124. Min Act: -0.0000

Data Index: 355469 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0123. Min Act: -0.0000

Data Index: 1396291 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0123. Min Act: -0.0000

Data Index: 720794 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0119. Min Act: -0.0000

Data Index: 388700 (The Pile)

Max Activating Token Index: 934

Text #9

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0119. Min Act: -0.0000

Data Index: 742586 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0119. Min Act: -0.0000

Data Index: 126539 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0121. Min Act: -0.0000

Data Index: 1758543 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0116. Min Act: -0.0000

Data Index: 684551 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0113. Min Act: -0.0000

Data Index: 135669 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0111. Min Act: -0.0000

Data Index: 1805965 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0110. Min Act: -0.0000

Data Index: 1935401 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0106. Min Act: -0.0000

Data Index: 1487114 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0104. Min Act: -0.0000

Data Index: 623107 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0108. Min Act: -0.0000

Data Index: 1735290 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0107. Min Act: -0.0000

Data Index: 1428685 (The Pile)

Max Activating Token Index: 962