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

Dataset: The Pile

Neuron 4685 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: 0.3744. Min Range: -0.3744

Max Act: 0.3744. Min Act: -0.0000

Data Index: 204810 (The Pile)

Max Activating Token Index: 771

Text #1

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3512. Min Act: -0.0000

Data Index: 797278 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3132. Min Act: -0.0000

Data Index: 159648 (The Pile)

Max Activating Token Index: 770

Text #3

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1438101 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2936. Min Act: -0.0000

Data Index: 161186 (The Pile)

Max Activating Token Index: 54

Text #5

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2971. Min Act: -0.0000

Data Index: 380521 (The Pile)

Max Activating Token Index: 33

Text #6

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1057960 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1712246 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1455129 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2906. Min Act: -0.0000

Data Index: 161473 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2814. Min Act: -0.0000

Data Index: 432243 (The Pile)

Max Activating Token Index: 131

Text #11

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2493. Min Act: -0.0000

Data Index: 546743 (The Pile)

Max Activating Token Index: 672

Text #12

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2787. Min Act: -0.0000

Data Index: 243903 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2719. Min Act: -0.0000

Data Index: 412863 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1122728 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2657. Min Act: -0.0000

Data Index: 833845 (The Pile)

Max Activating Token Index: 616

Text #16

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3016. Min Act: -0.0000

Data Index: 823573 (The Pile)

Max Activating Token Index: 284

Text #17

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2489. Min Act: -0.0000

Data Index: 128803 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2638. Min Act: -0.0000

Data Index: 270592 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1980657 (The Pile)

Max Activating Token Index: 634