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

Dataset: The Pile

Neuron 3204 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0545. Min Range: -1.0545

Max Act: 1.0545. Min Act: -0.0000

Data Index: 438103 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9749. Min Act: -0.0000

Data Index: 13075 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8718. Min Act: -0.0000

Data Index: 277134 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1052793 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8864. Min Act: -0.0000

Data Index: 142133 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1001825 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8812. Min Act: -0.0000

Data Index: 268778 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1044552 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1978607 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1138487 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8958. Min Act: -0.0000

Data Index: 571074 (The Pile)

Max Activating Token Index: 830

Text #11

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8072. Min Act: -0.0000

Data Index: 290319 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1872197 (The Pile)

Max Activating Token Index: 170

Text #13

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8162. Min Act: -0.0000

Data Index: 482823 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1261746 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.7807. Min Act: -0.0000

Data Index: 102040 (The Pile)

Max Activating Token Index: 102

Text #16

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1804222 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.7646. Min Act: -0.0000

Data Index: 3382 (The Pile)

Max Activating Token Index: 143

Text #18

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.6287. Min Act: -0.0000

Data Index: 331786 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.7666. Min Act: -0.0000

Data Index: 483570 (The Pile)

Max Activating Token Index: 393