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

Dataset: The Pile

Neuron 1983 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.4472. Min Act: -0.0000

Data Index: 797187 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2388. Min Act: -0.0000

Data Index: 645723 (The Pile)

Max Activating Token Index: 873

Text #2

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.1924. Min Act: -0.0000

Data Index: 1492197 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2124. Min Act: -0.0000

Data Index: 1086932 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.0463. Min Act: -0.0000

Data Index: 634721 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 1.4472. Min Range: -1.4472

Max Act: 0.9710. Min Act: -0.0000

Data Index: 931846 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.1372. Min Act: -0.0000

Data Index: 265651 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.0162. Min Act: -0.0000

Data Index: 1298118 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 1.4472. Min Range: -1.4472

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1510198 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1489067 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.0202. Min Act: -0.0000

Data Index: 249475 (The Pile)

Max Activating Token Index: 875

Text #11

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1143727 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1571608 (The Pile)

Max Activating Token Index: 25

Text #13

Max Range: 1.4472. Min Range: -1.4472

Max Act: 0.9750. Min Act: -0.0000

Data Index: 862325 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 1.4472. Min Range: -1.4472

Max Act: 0.9685. Min Act: -0.0000

Data Index: 842123 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 1.4472. Min Range: -1.4472

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1717976 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1892988 (The Pile)

Max Activating Token Index: 897

Text #17

Max Range: 1.4472. Min Range: -1.4472

Max Act: 0.9912. Min Act: -0.0000

Data Index: 591857 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.0811. Min Act: -0.0000

Data Index: 685193 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 1.4472. Min Range: -1.4472

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1161748 (The Pile)

Max Activating Token Index: 94