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

Dataset: The Pile

Neuron 738 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.7554. Min Act: -0.0000

Data Index: 56361 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.6670. Min Act: 0.0001

Data Index: 1193495 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.6492. Min Act: 0.0000

Data Index: 1968472 (The Pile)

Max Activating Token Index: 585

Text #3

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.6638. Min Act: -0.0000

Data Index: 909452 (The Pile)

Max Activating Token Index: 556

Text #4

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.6175. Min Act: 0.0000

Data Index: 974725 (The Pile)

Max Activating Token Index: 1008

Text #5

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.5119. Min Act: -0.0000

Data Index: 503951 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.3750. Min Act: -0.0000

Data Index: 1446064 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.4112. Min Act: 0.0001

Data Index: 622562 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.3563. Min Act: -0.0000

Data Index: 966084 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1882322 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1352306 (The Pile)

Max Activating Token Index: 575

Text #11

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.3147. Min Act: 0.0001

Data Index: 987629 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.2072. Min Act: -0.0000

Data Index: 679787 (The Pile)

Max Activating Token Index: 389

Text #13

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.0627. Min Act: -0.0000

Data Index: 192265 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.0314. Min Act: -0.0000

Data Index: 530880 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.1111. Min Act: -0.0000

Data Index: 217822 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.0038. Min Act: 0.0000

Data Index: 1523469 (The Pile)

Max Activating Token Index: 750

Text #17

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.1141. Min Act: 0.0000

Data Index: 1523565 (The Pile)

Max Activating Token Index: 609

Text #18

Max Range: 1.7554. Min Range: -1.7554

Max Act: 0.8856. Min Act: -0.0000

Data Index: 470294 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 1.7554. Min Range: -1.7554

Max Act: 0.9340. Min Act: 0.0000

Data Index: 427339 (The Pile)

Max Activating Token Index: 729