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

Dataset: The Pile

Neuron 3610 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1170643 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1520724 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1836591 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4145. Min Act: -0.0000

Data Index: 632071 (The Pile)

Max Activating Token Index: 767

Text #4

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4273. Min Act: -0.0000

Data Index: 593908 (The Pile)

Max Activating Token Index: 536

Text #5

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3841. Min Act: -0.0000

Data Index: 305944 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4013. Min Act: -0.0000

Data Index: 29839 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1922741 (The Pile)

Max Activating Token Index: 846

Text #8

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1757523 (The Pile)

Max Activating Token Index: 586

Text #9

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1097677 (The Pile)

Max Activating Token Index: 505

Text #10

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1092168 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3671. Min Act: -0.0000

Data Index: 720461 (The Pile)

Max Activating Token Index: 878

Text #12

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3620. Min Act: -0.0000

Data Index: 450690 (The Pile)

Max Activating Token Index: 600

Text #13

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1872336 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1489440 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3584. Min Act: -0.0000

Data Index: 367957 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3524. Min Act: -0.0000

Data Index: 309484 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1829675 (The Pile)

Max Activating Token Index: 991

Text #18

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3608. Min Act: -0.0000

Data Index: 831504 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1921077 (The Pile)

Max Activating Token Index: 685