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

Dataset: The Pile

Neuron 844 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5307. Min Range: -1.5307

Max Act: 1.5307. Min Act: 0.0000

Data Index: 1026912 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 1.5307. Min Range: -1.5307

Max Act: 1.3746. Min Act: 0.0000

Data Index: 601476 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 1.5307. Min Range: -1.5307

Max Act: 1.0339. Min Act: -0.0000

Data Index: 820300 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1979376 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1390740 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.7034. Min Act: -0.0000

Data Index: 192811 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.8121. Min Act: -0.0000

Data Index: 88762 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6452. Min Act: -0.0000

Data Index: 916614 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6293. Min Act: 0.0000

Data Index: 845247 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1383970 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6081. Min Act: -0.0000

Data Index: 870129 (The Pile)

Max Activating Token Index: 674

Text #11

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5696. Min Act: -0.0000

Data Index: 259374 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5136. Min Act: 0.0000

Data Index: 1482402 (The Pile)

Max Activating Token Index: 854

Text #13

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1218547 (The Pile)

Max Activating Token Index: 170

Text #14

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5521. Min Act: 0.0000

Data Index: 790003 (The Pile)

Max Activating Token Index: 520

Text #15

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1956053 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1381984 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1808339 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1820465 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.4962. Min Act: -0.0000

Data Index: 130689 (The Pile)

Max Activating Token Index: 450