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

Dataset: The Pile

Neuron 4216 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.6819. Min Act: -0.0000

Data Index: 527835 (The Pile)

Max Activating Token Index: 212

Text #1

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1091558 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.3790. Min Act: -0.0000

Data Index: 671632 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1956051 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1997687 (The Pile)

Max Activating Token Index: 735

Text #5

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.3480. Min Act: -0.0000

Data Index: 962497 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.3449. Min Act: -0.0000

Data Index: 1053496 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1870296 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.2642. Min Act: -0.0000

Data Index: 775248 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1110915 (The Pile)

Max Activating Token Index: 951

Text #10

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1858520 (The Pile)

Max Activating Token Index: 688

Text #11

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1410956 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.2953. Min Act: -0.0000

Data Index: 716426 (The Pile)

Max Activating Token Index: 558

Text #13

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1151025 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.2663. Min Act: -0.0000

Data Index: 21663 (The Pile)

Max Activating Token Index: 935

Text #15

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.2836. Min Act: -0.0000

Data Index: 382478 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1921846 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1124849 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1273659 (The Pile)

Max Activating Token Index: 154

Text #19

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.2384. Min Act: -0.0000

Data Index: 238659 (The Pile)

Max Activating Token Index: 57