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

Dataset: The Pile

Neuron 50 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: 0.9233. Min Range: -0.9233

Max Act: 0.8962. Min Act: -0.0000

Data Index: 1692728 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1682223 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7544. Min Act: -0.0000

Data Index: 501784 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8672. Min Act: -0.0000

Data Index: 681740 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8446. Min Act: -0.0000

Data Index: 15975 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1842636 (The Pile)

Max Activating Token Index: 785

Text #6

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1847515 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7708. Min Act: -0.0000

Data Index: 900472 (The Pile)

Max Activating Token Index: 821

Text #8

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1250088 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1294006 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1976613 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8228. Min Act: -0.0000

Data Index: 1112059 (The Pile)

Max Activating Token Index: 743

Text #12

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1607472 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1576867 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8182. Min Act: -0.0000

Data Index: 355243 (The Pile)

Max Activating Token Index: 944

Text #15

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7912. Min Act: -0.0000

Data Index: 916797 (The Pile)

Max Activating Token Index: 882

Text #16

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8680. Min Act: -0.0000

Data Index: 597345 (The Pile)

Max Activating Token Index: 732

Text #17

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8360. Min Act: -0.0000

Data Index: 122617 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7559. Min Act: -0.0000

Data Index: 111248 (The Pile)

Max Activating Token Index: 643

Text #19

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1079464 (The Pile)

Max Activating Token Index: 486