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

Dataset: The Pile

Neuron 2027 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: 0.1352. Min Range: -0.1352

Max Act: 0.1329. Min Act: -0.0000

Data Index: 668229 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1307. Min Act: -0.0000

Data Index: 597689 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1352. Min Act: -0.0000

Data Index: 916063 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1279. Min Act: 0.0000

Data Index: 1985037 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1257. Min Act: -0.0000

Data Index: 150757 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1229. Min Act: -0.0000

Data Index: 978855 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1230. Min Act: -0.0000

Data Index: 976012 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1211. Min Act: 0.0000

Data Index: 72331 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1174927 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1937487 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1605687 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1120. Min Act: -0.0000

Data Index: 65533 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1361430 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1884205 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1087. Min Act: -0.0000

Data Index: 495050 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1124. Min Act: 0.0000

Data Index: 419230 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1845227 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1075. Min Act: -0.0000

Data Index: 886339 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1314391 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1504165 (The Pile)

Max Activating Token Index: 1023