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

Dataset: The Pile

Neuron 313 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.7369. Min Act: -0.0000

Data Index: 797543 (The Pile)

Max Activating Token Index: 733

Text #1

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6961. Min Act: -0.0000

Data Index: 95922 (The Pile)

Max Activating Token Index: 889

Text #2

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6433. Min Act: -0.0000

Data Index: 367317 (The Pile)

Max Activating Token Index: 670

Text #3

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1516295 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1514157 (The Pile)

Max Activating Token Index: 616

Text #5

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5824. Min Act: -0.0000

Data Index: 544980 (The Pile)

Max Activating Token Index: 842

Text #6

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1678013 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1958308 (The Pile)

Max Activating Token Index: 448

Text #8

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1698362 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5519. Min Act: -0.0000

Data Index: 194113 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1007849 (The Pile)

Max Activating Token Index: 523

Text #11

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5753. Min Act: -0.0000

Data Index: 262408 (The Pile)

Max Activating Token Index: 875

Text #12

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5375. Min Act: -0.0000

Data Index: 587346 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5334. Min Act: -0.0000

Data Index: 667084 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5012. Min Act: -0.0000

Data Index: 984773 (The Pile)

Max Activating Token Index: 312

Text #15

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5129. Min Act: -0.0000

Data Index: 18790 (The Pile)

Max Activating Token Index: 774

Text #16

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1917304 (The Pile)

Max Activating Token Index: 832

Text #17

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5223. Min Act: 0.0000

Data Index: 1678169 (The Pile)

Max Activating Token Index: 950

Text #18

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1263951 (The Pile)

Max Activating Token Index: 706

Text #19

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5101. Min Act: -0.0000

Data Index: 216295 (The Pile)

Max Activating Token Index: 827