Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2850 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.9557. Min Act: 0.0000

Data Index: 518373 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8203. Min Act: -0.0000

Data Index: 1394728 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.6834. Min Act: -0.0000

Data Index: 741004 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.5567. Min Act: -0.0000

Data Index: 952974 (The Pile)

Max Activating Token Index: 985

Text #4

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.3931. Min Act: -0.0000

Data Index: 1998816 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.4512. Min Act: -0.0000

Data Index: 695565 (The Pile)

Max Activating Token Index: 873

Text #6

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.3580. Min Act: -0.0000

Data Index: 1583301 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.7782. Min Act: -0.0000

Data Index: 134213 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.4288. Min Act: -0.0000

Data Index: 344781 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.5220. Min Act: -0.0000

Data Index: 1083704 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.2224. Min Act: -0.0000

Data Index: 924435 (The Pile)

Max Activating Token Index: 824

Text #11

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.3740. Min Act: 0.0000

Data Index: 1852398 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.4562. Min Act: -0.0000

Data Index: 175571 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.2383. Min Act: -0.0000

Data Index: 1599726 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.1805. Min Act: -0.0000

Data Index: 1191785 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.3109. Min Act: -0.0000

Data Index: 1990882 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.4838. Min Act: -0.0000

Data Index: 678418 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 2.9557. Min Range: -2.9557

Max Act: 1.9833. Min Act: -0.0000

Data Index: 1402244 (The Pile)

Max Activating Token Index: 880

Text #18

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.3533. Min Act: -0.0000

Data Index: 182665 (The Pile)

Max Activating Token Index: 946

Text #19

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.5887. Min Act: -0.0000

Data Index: 567212 (The Pile)

Max Activating Token Index: 601