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

Dataset: The Pile

Neuron 2660 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.9013. Min Act: -0.0000

Data Index: 1351734 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.6928. Min Act: -0.0000

Data Index: 1452838 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.5911. Min Act: -0.0000

Data Index: 670156 (The Pile)

Max Activating Token Index: 639

Text #3

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.6532. Min Act: -0.0000

Data Index: 1706314 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.5721. Min Act: -0.0000

Data Index: 69066 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1956135 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.4454. Min Act: -0.0000

Data Index: 1023511 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.4022. Min Act: -0.0000

Data Index: 336170 (The Pile)

Max Activating Token Index: 144

Text #8

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.3840. Min Act: -0.0000

Data Index: 1793198 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.3316. Min Act: -0.0000

Data Index: 85974 (The Pile)

Max Activating Token Index: 904

Text #10

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.3315. Min Act: -0.0000

Data Index: 1499814 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.3739. Min Act: -0.0000

Data Index: 1076220 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.2977. Min Act: -0.0000

Data Index: 877683 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.1657. Min Act: -0.0000

Data Index: 534108 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.2260. Min Act: -0.0000

Data Index: 116575 (The Pile)

Max Activating Token Index: 818

Text #15

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.2149. Min Act: -0.0000

Data Index: 1797945 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.1948. Min Act: -0.0000

Data Index: 221643 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1480457 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.1800. Min Act: -0.0000

Data Index: 1491219 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.1642. Min Act: -0.0000

Data Index: 929824 (The Pile)

Max Activating Token Index: 618