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

Dataset: The Pile

Neuron 3169 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1309. Min Act: -0.0000

Data Index: 206318 (The Pile)

Max Activating Token Index: 920

Text #1

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1287. Min Act: -0.0000

Data Index: 867354 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1249. Min Act: -0.0000

Data Index: 702141 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1232. Min Act: -0.0000

Data Index: 882767 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1164. Min Act: -0.0000

Data Index: 662633 (The Pile)

Max Activating Token Index: 916

Text #5

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1959471 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1123525 (The Pile)

Max Activating Token Index: 789

Text #7

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1145. Min Act: -0.0000

Data Index: 464977 (The Pile)

Max Activating Token Index: 67

Text #8

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1118. Min Act: -0.0000

Data Index: 196437 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1857025 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1660756 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1457391 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1082. Min Act: -0.0000

Data Index: 829146 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1574449 (The Pile)

Max Activating Token Index: 597

Text #14

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1747748 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1409880 (The Pile)

Max Activating Token Index: 942

Text #16

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1627973 (The Pile)

Max Activating Token Index: 477

Text #17

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1022. Min Act: -0.0000

Data Index: 85740 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1623395 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0936. Min Act: -0.0000

Data Index: 830103 (The Pile)

Max Activating Token Index: 998