Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2663 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1532809 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.6224. Min Act: -0.0000

Data Index: 720802 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5921. Min Act: -0.0000

Data Index: 856386 (The Pile)

Max Activating Token Index: 682

Text #3

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5845. Min Act: -0.0000

Data Index: 1921081 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1919545 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1607398 (The Pile)

Max Activating Token Index: 963

Text #6

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1438409 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.4829. Min Act: -0.0000

Data Index: 442241 (The Pile)

Max Activating Token Index: 907

Text #8

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1951805 (The Pile)

Max Activating Token Index: 634

Text #9

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1428362 (The Pile)

Max Activating Token Index: 269

Text #10

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.4794. Min Act: -0.0000

Data Index: 627296 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1890210 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1129393 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.4660. Min Act: -0.0000

Data Index: 407273 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.4880. Min Act: -0.0000

Data Index: 269161 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.4935. Min Act: -0.0001

Data Index: 1188467 (The Pile)

Max Activating Token Index: 697

Text #16

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.4913. Min Act: -0.0001

Data Index: 803890 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.4754. Min Act: -0.0000

Data Index: 124508 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5009. Min Act: -0.0000

Data Index: 312439 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1694830 (The Pile)

Max Activating Token Index: 637