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

Dataset: The Pile

Neuron 645 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: 0.9113. Min Range: -0.9113

Max Act: 0.9113. Min Act: -0.0000

Data Index: 241078 (The Pile)

Max Activating Token Index: 871

Text #1

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1551877 (The Pile)

Max Activating Token Index: 574

Text #2

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.8180. Min Act: -0.0000

Data Index: 494833 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1214717 (The Pile)

Max Activating Token Index: 644

Text #4

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.8472. Min Act: -0.0000

Data Index: 879217 (The Pile)

Max Activating Token Index: 75

Text #5

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.8617. Min Act: -0.0000

Data Index: 757183 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7094. Min Act: -0.0000

Data Index: 744080 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1729694 (The Pile)

Max Activating Token Index: 243

Text #8

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1820653 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7070. Min Act: -0.0000

Data Index: 224237 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1253346 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7848. Min Act: -0.0000

Data Index: 211740 (The Pile)

Max Activating Token Index: 344

Text #12

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6959. Min Act: -0.0000

Data Index: 586589 (The Pile)

Max Activating Token Index: 244

Text #13

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6854. Min Act: -0.0000

Data Index: 105890 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1824289 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6440. Min Act: -0.0000

Data Index: 948644 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6325. Min Act: -0.0000

Data Index: 574479 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1315684 (The Pile)

Max Activating Token Index: 566

Text #18

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1658564 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6237. Min Act: -0.0000

Data Index: 818588 (The Pile)

Max Activating Token Index: 616