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

Dataset: The Pile

Neuron 2260 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: 5.1697. Min Range: -5.1697

Max Act: 5.1697. Min Act: -0.0000

Data Index: 109252 (The Pile)

Max Activating Token Index: 863

Text #1

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.7203. Min Act: -0.0000

Data Index: 1521754 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.2413. Min Act: -0.0000

Data Index: 194949 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.2100. Min Act: -0.0000

Data Index: 84973 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.3305. Min Act: -0.0000

Data Index: 591088 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.6990. Min Act: -0.0000

Data Index: 676610 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.1844. Min Act: -0.0000

Data Index: 557084 (The Pile)

Max Activating Token Index: 742

Text #7

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.5366. Min Act: -0.0000

Data Index: 331452 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.2585. Min Act: -0.0000

Data Index: 1239912 (The Pile)

Max Activating Token Index: 739

Text #9

Max Range: 5.1697. Min Range: -5.1697

Max Act: 3.9860. Min Act: -0.0000

Data Index: 781466 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.1211. Min Act: -0.0000

Data Index: 1779795 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 5.1697. Min Range: -5.1697

Max Act: 3.9279. Min Act: -0.0000

Data Index: 870512 (The Pile)

Max Activating Token Index: 769

Text #12

Max Range: 5.1697. Min Range: -5.1697

Max Act: 3.9649. Min Act: -0.0000

Data Index: 1026881 (The Pile)

Max Activating Token Index: 589

Text #13

Max Range: 5.1697. Min Range: -5.1697

Max Act: 3.8618. Min Act: -0.0000

Data Index: 561665 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 5.1697. Min Range: -5.1697

Max Act: 3.7178. Min Act: -0.0000

Data Index: 99027 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.2487. Min Act: -0.0000

Data Index: 316873 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.0439. Min Act: -0.0000

Data Index: 1929446 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.0142. Min Act: -0.0000

Data Index: 1637127 (The Pile)

Max Activating Token Index: 909

Text #18

Max Range: 5.1697. Min Range: -5.1697

Max Act: 4.0851. Min Act: -0.0000

Data Index: 1320458 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 5.1697. Min Range: -5.1697

Max Act: 3.6009. Min Act: -0.0000

Data Index: 521589 (The Pile)

Max Activating Token Index: 492