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

Dataset: The Pile

Neuron 1617 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: 3.7451. Min Range: -3.7451

Max Act: 3.7451. Min Act: -0.0000

Data Index: 826481 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.3480. Min Act: -0.0000

Data Index: 875554 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.3732. Min Act: -0.0000

Data Index: 1004404 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.3165. Min Act: -0.0000

Data Index: 904432 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.2603. Min Act: -0.0000

Data Index: 1919331 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.0549. Min Act: -0.0000

Data Index: 1698656 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.0449. Min Act: -0.0000

Data Index: 985106 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.1858. Min Act: -0.0000

Data Index: 42988 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.0494. Min Act: -0.0000

Data Index: 706047 (The Pile)

Max Activating Token Index: 490

Text #9

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.1553. Min Act: -0.0000

Data Index: 355897 (The Pile)

Max Activating Token Index: 501

Text #10

Max Range: 3.7451. Min Range: -3.7451

Max Act: 2.8703. Min Act: -0.0000

Data Index: 1861971 (The Pile)

Max Activating Token Index: 994

Text #11

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.1242. Min Act: -0.0000

Data Index: 986007 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.1546. Min Act: -0.0000

Data Index: 717220 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 3.7451. Min Range: -3.7451

Max Act: 2.9574. Min Act: -0.0000

Data Index: 61659 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.1144. Min Act: -0.0000

Data Index: 1512696 (The Pile)

Max Activating Token Index: 36

Text #15

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.0910. Min Act: -0.0000

Data Index: 318531 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.0529. Min Act: -0.0000

Data Index: 1872317 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.0415. Min Act: -0.0000

Data Index: 1061733 (The Pile)

Max Activating Token Index: 574

Text #18

Max Range: 3.7451. Min Range: -3.7451

Max Act: 2.9980. Min Act: -0.0000

Data Index: 1636378 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.1053. Min Act: -0.0000

Data Index: 1025632 (The Pile)

Max Activating Token Index: 379