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

Dataset: The Pile

Neuron 4962 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: 1.8284. Min Range: -1.8284

Max Act: 1.6642. Min Act: -0.0000

Data Index: 713996 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.8284. Min Act: -0.0000

Data Index: 1990083 (The Pile)

Max Activating Token Index: 637

Text #2

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.6121. Min Act: -0.0000

Data Index: 1317844 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.6114. Min Act: -0.0000

Data Index: 536036 (The Pile)

Max Activating Token Index: 509

Text #4

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7689. Min Act: -0.0000

Data Index: 984738 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.4704. Min Act: -0.0000

Data Index: 621681 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.5029. Min Act: -0.0000

Data Index: 1805499 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.5136. Min Act: -0.0000

Data Index: 94525 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.5196. Min Act: -0.0000

Data Index: 988139 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.5025. Min Act: -0.0000

Data Index: 887758 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1861851 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.4861. Min Act: -0.0000

Data Index: 1623661 (The Pile)

Max Activating Token Index: 167

Text #12

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1602136 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.3111. Min Act: -0.0000

Data Index: 247042 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.4194. Min Act: -0.0000

Data Index: 962030 (The Pile)

Max Activating Token Index: 35

Text #15

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.2731. Min Act: -0.0000

Data Index: 465178 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.3941. Min Act: -0.0000

Data Index: 807576 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.3330. Min Act: -0.0000

Data Index: 1590672 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.3295. Min Act: -0.0000

Data Index: 1018254 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.2629. Min Act: -0.0000

Data Index: 1136716 (The Pile)

Max Activating Token Index: 455