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

Dataset: The Pile

Neuron 1272 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1043638 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1175526 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1000066 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2227. Min Act: -0.0001

Data Index: 380869 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1891. Min Act: -0.0000

Data Index: 419642 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1951. Min Act: -0.0000

Data Index: 901455 (The Pile)

Max Activating Token Index: 110

Text #6

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1962179 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1807. Min Act: -0.0000

Data Index: 316896 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1583930 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1488608 (The Pile)

Max Activating Token Index: 764

Text #10

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1312214 (The Pile)

Max Activating Token Index: 148

Text #11

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1487. Min Act: -0.0000

Data Index: 674506 (The Pile)

Max Activating Token Index: 588

Text #12

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1850041 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1622. Min Act: -0.0000

Data Index: 168481 (The Pile)

Max Activating Token Index: 455

Text #14

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1914407 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1524. Min Act: -0.0000

Data Index: 316598 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1559. Min Act: -0.0000

Data Index: 147942 (The Pile)

Max Activating Token Index: 1004

Text #17

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1608303 (The Pile)

Max Activating Token Index: 513

Text #18

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1769. Min Act: -0.0000

Data Index: 35083 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1692. Min Act: -0.0000

Data Index: 477479 (The Pile)

Max Activating Token Index: 481