Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3820 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1835. Min Act: -0.0000

Data Index: 355584 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1533. Min Act: -0.0000

Data Index: 822057 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1672. Min Act: -0.0000

Data Index: 115721 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1368. Min Act: -0.0000

Data Index: 739612 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1171843 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1434484 (The Pile)

Max Activating Token Index: 439

Text #6

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1386. Min Act: -0.0000

Data Index: 735539 (The Pile)

Max Activating Token Index: 876

Text #7

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1298. Min Act: -0.0000

Data Index: 390482 (The Pile)

Max Activating Token Index: 78

Text #8

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1575936 (The Pile)

Max Activating Token Index: 405

Text #9

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1090575 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1602718 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1157644 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1132. Min Act: -0.0000

Data Index: 834158 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1114. Min Act: -0.0000

Data Index: 984078 (The Pile)

Max Activating Token Index: 89

Text #14

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1336896 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1149. Min Act: -0.0000

Data Index: 520288 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1427640 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1121. Min Act: -0.0000

Data Index: 385109 (The Pile)

Max Activating Token Index: 201

Text #18

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1075. Min Act: -0.0000

Data Index: 448139 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1142. Min Act: -0.0000

Data Index: 749470 (The Pile)

Max Activating Token Index: 999