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

Dataset: The Pile

Neuron 2123 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: 1.1929. Min Range: -1.1929

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1204846 (The Pile)

Max Activating Token Index: 357

Text #1

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9445. Min Act: -0.0000

Data Index: 171102 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.0194. Min Act: -0.0000

Data Index: 999019 (The Pile)

Max Activating Token Index: 681

Text #3

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9589. Min Act: -0.0000

Data Index: 1159915 (The Pile)

Max Activating Token Index: 577

Text #4

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1986553 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1503849 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1325931 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9980. Min Act: -0.0000

Data Index: 1604498 (The Pile)

Max Activating Token Index: 996

Text #8

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1602005 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9543. Min Act: -0.0000

Data Index: 531580 (The Pile)

Max Activating Token Index: 117

Text #10

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9393. Min Act: -0.0000

Data Index: 1866950 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1114668 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1311641 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1004948 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1050299 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8698. Min Act: -0.0000

Data Index: 673136 (The Pile)

Max Activating Token Index: 158

Text #16

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1663807 (The Pile)

Max Activating Token Index: 872

Text #17

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1876011 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8048. Min Act: -0.0000

Data Index: 866015 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1026882 (The Pile)

Max Activating Token Index: 881