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

Dataset: The Pile

Neuron 4864 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: 0.1437. Min Range: -0.1437

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1869799 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1287. Min Act: -0.0000

Data Index: 664553 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1242. Min Act: -0.0000

Data Index: 712423 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1847001 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1477205 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1958747 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1977640 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1137. Min Act: -0.0000

Data Index: 295589 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1131. Min Act: -0.0000

Data Index: 860411 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1887489 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1363787 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1774603 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1050. Min Act: -0.0000

Data Index: 1044999 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1795661 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1069. Min Act: -0.0000

Data Index: 794591 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1058. Min Act: -0.0000

Data Index: 708423 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1670139 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1007. Min Act: -0.0000

Data Index: 938516 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1925100 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1420511 (The Pile)

Max Activating Token Index: 1023