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

Dataset: The Pile

Neuron 3072 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1167746 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1815609 (The Pile)

Max Activating Token Index: 525

Text #2

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1591849 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9801. Min Act: -0.0000

Data Index: 372789 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1327553 (The Pile)

Max Activating Token Index: 560

Text #5

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.7927. Min Act: -0.0000

Data Index: 884037 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8367. Min Act: -0.0000

Data Index: 524303 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8141. Min Act: -0.0000

Data Index: 21773 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.6568. Min Act: -0.0000

Data Index: 662731 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1826881 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.7192. Min Act: -0.0000

Data Index: 847820 (The Pile)

Max Activating Token Index: 601

Text #11

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.5766. Min Act: -0.0000

Data Index: 700975 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.6124. Min Act: -0.0000

Data Index: 661789 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.7045. Min Act: -0.0000

Data Index: 833365 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.7374. Min Act: 0.0000

Data Index: 595222 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.6262. Min Act: -0.0000

Data Index: 539832 (The Pile)

Max Activating Token Index: 730

Text #16

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1943916 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.6485. Min Act: -0.0000

Data Index: 632430 (The Pile)

Max Activating Token Index: 585

Text #18

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1937076 (The Pile)

Max Activating Token Index: 403

Text #19

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.5875. Min Act: -0.0000

Data Index: 558151 (The Pile)

Max Activating Token Index: 804