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

Dataset: The Pile

Neuron 4442 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: 1.7152. Min Range: -1.7152

Max Act: 1.7152. Min Act: -0.0000

Data Index: 683704 (The Pile)

Max Activating Token Index: 920

Text #1

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.4907. Min Act: -0.0000

Data Index: 783933 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.3915. Min Act: -0.0000

Data Index: 1466665 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.4100. Min Act: -0.0000

Data Index: 77325 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.3014. Min Act: -0.0000

Data Index: 1673869 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.2724. Min Act: -0.0000

Data Index: 738650 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.1782. Min Act: -0.0000

Data Index: 1913154 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.1534. Min Act: -0.0000

Data Index: 93204 (The Pile)

Max Activating Token Index: 724

Text #8

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.1928. Min Act: -0.0000

Data Index: 119593 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.1562. Min Act: -0.0000

Data Index: 740652 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.1555. Min Act: -0.0000

Data Index: 506987 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1676566 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.1815. Min Act: -0.0000

Data Index: 142617 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.1806. Min Act: -0.0000

Data Index: 321552 (The Pile)

Max Activating Token Index: 352

Text #14

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.1558. Min Act: -0.0000

Data Index: 536997 (The Pile)

Max Activating Token Index: 994

Text #15

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1787763 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.0835. Min Act: -0.0000

Data Index: 401075 (The Pile)

Max Activating Token Index: 678

Text #17

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1125370 (The Pile)

Max Activating Token Index: 760

Text #18

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.0873. Min Act: -0.0000

Data Index: 747826 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 1.7152. Min Range: -1.7152

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1646803 (The Pile)

Max Activating Token Index: 662