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

Dataset: The Pile

Neuron 3504 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: 0.1336. Min Range: -0.1336

Max Act: 0.1336. Min Act: 0.0000

Data Index: 108539 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1807478 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1148. Min Act: -0.0000

Data Index: 921569 (The Pile)

Max Activating Token Index: 5

Text #3

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1879955 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1828526 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1121. Min Act: -0.0000

Data Index: 439664 (The Pile)

Max Activating Token Index: 4

Text #6

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1113. Min Act: -0.0000

Data Index: 363684 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1106. Min Act: -0.0000

Data Index: 142720 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1099. Min Act: -0.0000

Data Index: 531318 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1633952 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1082. Min Act: -0.0000

Data Index: 556335 (The Pile)

Max Activating Token Index: 4

Text #11

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1088. Min Act: -0.0000

Data Index: 776002 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1126. Min Act: 0.0000

Data Index: 191141 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1124. Min Act: -0.0000

Data Index: 340346 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1080. Min Act: 0.0000

Data Index: 188624 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1123. Min Act: -0.0000

Data Index: 959500 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1704286 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1072. Min Act: -0.0000

Data Index: 134522 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1225633 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1066. Min Act: -0.0000

Data Index: 54444 (The Pile)

Max Activating Token Index: 1023