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

Dataset: The Pile

Neuron 4072 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: 0.3719. Min Range: -0.3719

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1322407 (The Pile)

Max Activating Token Index: 249

Text #1

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1409692 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3411. Min Act: -0.0000

Data Index: 789560 (The Pile)

Max Activating Token Index: 720

Text #3

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1030642 (The Pile)

Max Activating Token Index: 540

Text #4

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1798639 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1421781 (The Pile)

Max Activating Token Index: 571

Text #6

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1148759 (The Pile)

Max Activating Token Index: 405

Text #7

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1973718 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3079. Min Act: -0.0000

Data Index: 133116 (The Pile)

Max Activating Token Index: 518

Text #9

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2954. Min Act: -0.0000

Data Index: 476452 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3040. Min Act: -0.0000

Data Index: 339421 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2899. Min Act: -0.0000

Data Index: 854841 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2918. Min Act: -0.0000

Data Index: 465194 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1511778 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1925787 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1341678 (The Pile)

Max Activating Token Index: 697

Text #16

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1497702 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1782037 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2647. Min Act: -0.0000

Data Index: 382803 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1625846 (The Pile)

Max Activating Token Index: 382