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

Dataset: The Pile

Neuron 3196 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1942977 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1785. Min Act: -0.0000

Data Index: 722868 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1807. Min Act: -0.0000

Data Index: 958555 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1565. Min Act: -0.0000

Data Index: 122731 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1430. Min Act: -0.0000

Data Index: 223098 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1247. Min Act: -0.0000

Data Index: 893988 (The Pile)

Max Activating Token Index: 961

Text #6

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1863757 (The Pile)

Max Activating Token Index: 806

Text #7

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1433. Min Act: -0.0000

Data Index: 226113 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1330. Min Act: -0.0000

Data Index: 470183 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1208. Min Act: -0.0000

Data Index: 445930 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1185. Min Act: -0.0000

Data Index: 239461 (The Pile)

Max Activating Token Index: 881

Text #11

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1385249 (The Pile)

Max Activating Token Index: 762

Text #12

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1176. Min Act: -0.0000

Data Index: 919437 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1071403 (The Pile)

Max Activating Token Index: 793

Text #14

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1334. Min Act: -0.0000

Data Index: 979575 (The Pile)

Max Activating Token Index: 987

Text #15

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1603216 (The Pile)

Max Activating Token Index: 822

Text #16

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1002. Min Act: -0.0000

Data Index: 9904 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1343. Min Act: -0.0000

Data Index: 873948 (The Pile)

Max Activating Token Index: 929

Text #18

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1167175 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1350240 (The Pile)

Max Activating Token Index: 310