Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2670 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1368. Min Act: -0.0000

Data Index: 584999 (The Pile)

Max Activating Token Index: 592

Text #1

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1303. Min Act: -0.0000

Data Index: 395829 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1270. Min Act: -0.0001

Data Index: 839886 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1247. Min Act: -0.0000

Data Index: 359289 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1174. Min Act: -0.0000

Data Index: 24054 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1566951 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1156. Min Act: -0.0001

Data Index: 160233 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1174. Min Act: -0.0000

Data Index: 1075450 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1114. Min Act: -0.0001

Data Index: 929020 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1158. Min Act: -0.0000

Data Index: 257025 (The Pile)

Max Activating Token Index: 618

Text #10

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1621899 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1462363 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1962149 (The Pile)

Max Activating Token Index: 348

Text #13

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1081. Min Act: -0.0000

Data Index: 576122 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1443369 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1032. Min Act: -0.0000

Data Index: 356624 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1155. Min Act: -0.0000

Data Index: 920219 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1154186 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1039. Min Act: -0.0000

Data Index: 827130 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1400899 (The Pile)

Max Activating Token Index: 109