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

Dataset: The Pile

Neuron 2055 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.6620. Min Act: -0.0000

Data Index: 431007 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.5889. Min Act: -0.0000

Data Index: 280113 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.3092. Min Act: -0.0000

Data Index: 1209759 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.2906. Min Act: -0.0000

Data Index: 1001899 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.3904. Min Act: -0.0000

Data Index: 1493888 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 4.6620. Min Range: -4.6620

Max Act: 3.3621. Min Act: -0.0000

Data Index: 793825 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.1640. Min Act: -0.0000

Data Index: 1133250 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 4.6620. Min Range: -4.6620

Max Act: 3.6131. Min Act: -0.0000

Data Index: 1144905 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 4.6620. Min Range: -4.6620

Max Act: 3.2471. Min Act: -0.0000

Data Index: 391924 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 4.6620. Min Range: -4.6620

Max Act: 3.7072. Min Act: -0.0000

Data Index: 231057 (The Pile)

Max Activating Token Index: 210

Text #10

Max Range: 4.6620. Min Range: -4.6620

Max Act: 2.4281. Min Act: -0.0000

Data Index: 952846 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 4.6620. Min Range: -4.6620

Max Act: 3.7269. Min Act: -0.0000

Data Index: 1211376 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 4.6620. Min Range: -4.6620

Max Act: 3.9763. Min Act: -0.0000

Data Index: 343885 (The Pile)

Max Activating Token Index: 821

Text #13

Max Range: 4.6620. Min Range: -4.6620

Max Act: 3.4729. Min Act: -0.0000

Data Index: 1913604 (The Pile)

Max Activating Token Index: 701

Text #14

Max Range: 4.6620. Min Range: -4.6620

Max Act: 3.7653. Min Act: -0.0000

Data Index: 1691199 (The Pile)

Max Activating Token Index: 366

Text #15

Max Range: 4.6620. Min Range: -4.6620

Max Act: 3.4734. Min Act: -0.0000

Data Index: 1217953 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 4.6620. Min Range: -4.6620

Max Act: 3.8575. Min Act: -0.0000

Data Index: 1214031 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 4.6620. Min Range: -4.6620

Max Act: 3.4637. Min Act: -0.0000

Data Index: 363535 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 4.6620. Min Range: -4.6620

Max Act: 2.7468. Min Act: -0.0000

Data Index: 1808206 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 4.6620. Min Range: -4.6620

Max Act: 2.8995. Min Act: -0.0000

Data Index: 971425 (The Pile)

Max Activating Token Index: 809