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

Dataset: The Pile

Neuron 4649 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3788. Min Act: 0.0000

Data Index: 137744 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3726. Min Act: -0.0000

Data Index: 585052 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2902. Min Act: -0.0000

Data Index: 617961 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1499677 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1468584 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1908946 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2805. Min Act: -0.0000

Data Index: 981466 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1232753 (The Pile)

Max Activating Token Index: 593

Text #8

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1845478 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1414436 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2519. Min Act: 0.0000

Data Index: 1826995 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2896. Min Act: 0.0000

Data Index: 1851859 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1453787 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2919. Min Act: -0.0000

Data Index: 919363 (The Pile)

Max Activating Token Index: 874

Text #14

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1921411 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1252545 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1919436 (The Pile)

Max Activating Token Index: 586

Text #17

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1595428 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2631. Min Act: -0.0000

Data Index: 565975 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1703975 (The Pile)

Max Activating Token Index: 119