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

Dataset: The Pile

Neuron 3398 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: 1.3801. Min Range: -1.3801

Max Act: 1.2921. Min Act: -0.0000

Data Index: 127360 (The Pile)

Max Activating Token Index: 682

Text #1

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2946. Min Act: -0.0000

Data Index: 1250417 (The Pile)

Max Activating Token Index: 576

Text #2

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.3135. Min Act: -0.0000

Data Index: 1588557 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1986068 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.3801. Min Act: -0.0000

Data Index: 1074201 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2359. Min Act: -0.0000

Data Index: 338649 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2291. Min Act: -0.0000

Data Index: 753184 (The Pile)

Max Activating Token Index: 880

Text #7

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.3316. Min Act: -0.0000

Data Index: 1729368 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1503332 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2971. Min Act: -0.0000

Data Index: 1626711 (The Pile)

Max Activating Token Index: 122

Text #10

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2701. Min Act: -0.0000

Data Index: 121122 (The Pile)

Max Activating Token Index: 227

Text #11

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1766193 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2574. Min Act: -0.0000

Data Index: 1873585 (The Pile)

Max Activating Token Index: 506

Text #13

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1498681 (The Pile)

Max Activating Token Index: 54

Text #14

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2190. Min Act: -0.0000

Data Index: 120545 (The Pile)

Max Activating Token Index: 339

Text #15

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.1770. Min Act: -0.0000

Data Index: 962994 (The Pile)

Max Activating Token Index: 905

Text #16

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2013. Min Act: -0.0000

Data Index: 1051605 (The Pile)

Max Activating Token Index: 802

Text #17

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2096. Min Act: -0.0000

Data Index: 998042 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2448. Min Act: -0.0000

Data Index: 974423 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1110082 (The Pile)

Max Activating Token Index: 87