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

Dataset: The Pile

Neuron 641 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: 0.3133. Min Range: -0.3133

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1838377 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2456. Min Act: -0.0000

Data Index: 26212 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1687436 (The Pile)

Max Activating Token Index: 987

Text #3

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1897984 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1376551 (The Pile)

Max Activating Token Index: 424

Text #5

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2218. Min Act: -0.0000

Data Index: 972615 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2089. Min Act: 0.0000

Data Index: 77373 (The Pile)

Max Activating Token Index: 12

Text #7

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2057. Min Act: -0.0000

Data Index: 891623 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2175. Min Act: -0.0000

Data Index: 831980 (The Pile)

Max Activating Token Index: 682

Text #9

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1986977 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2008. Min Act: -0.0000

Data Index: 876857 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2126. Min Act: -0.0000

Data Index: 908123 (The Pile)

Max Activating Token Index: 229

Text #12

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1053434 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2017. Min Act: 0.0001

Data Index: 931307 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1363908 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1880904 (The Pile)

Max Activating Token Index: 659

Text #16

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1783. Min Act: -0.0000

Data Index: 482864 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1967837 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1927758 (The Pile)

Max Activating Token Index: 313

Text #19

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1951825 (The Pile)

Max Activating Token Index: 899