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

Dataset: The Pile

Neuron 195 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: 0.7852. Min Range: -0.7852

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1767732 (The Pile)

Max Activating Token Index: 685

Text #1

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7239. Min Act: -0.0000

Data Index: 239897 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7406. Min Act: -0.0000

Data Index: 31420 (The Pile)

Max Activating Token Index: 515

Text #3

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7288. Min Act: -0.0000

Data Index: 188080 (The Pile)

Max Activating Token Index: 426

Text #4

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1426075 (The Pile)

Max Activating Token Index: 771

Text #5

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1318157 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1298863 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7057. Min Act: -0.0000

Data Index: 153145 (The Pile)

Max Activating Token Index: 821

Text #8

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6759. Min Act: -0.0000

Data Index: 807766 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1450636 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1282840 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.5652. Min Act: -0.0000

Data Index: 164574 (The Pile)

Max Activating Token Index: 864

Text #12

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1118278 (The Pile)

Max Activating Token Index: 621

Text #13

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.5985. Min Act: -0.0000

Data Index: 714986 (The Pile)

Max Activating Token Index: 697

Text #14

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6304. Min Act: -0.0000

Data Index: 409778 (The Pile)

Max Activating Token Index: 728

Text #15

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6598. Min Act: -0.0000

Data Index: 227304 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1624196 (The Pile)

Max Activating Token Index: 25

Text #17

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6096. Min Act: -0.0000

Data Index: 523174 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.5852. Min Act: -0.0000

Data Index: 421587 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1886145 (The Pile)

Max Activating Token Index: 299