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

Dataset: The Pile

Neuron 1746 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.8313. Min Act: -0.0000

Data Index: 735225 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1636277 (The Pile)

Max Activating Token Index: 485

Text #2

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1698424 (The Pile)

Max Activating Token Index: 368

Text #3

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1755452 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6692. Min Act: -0.0000

Data Index: 845648 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1104050 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1109391 (The Pile)

Max Activating Token Index: 981

Text #7

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6474. Min Act: -0.0000

Data Index: 585619 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5888. Min Act: -0.0000

Data Index: 87583 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5848. Min Act: -0.0000

Data Index: 894125 (The Pile)

Max Activating Token Index: 981

Text #10

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1991057 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1096970 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5823. Min Act: -0.0000

Data Index: 74081 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6114. Min Act: -0.0000

Data Index: 561187 (The Pile)

Max Activating Token Index: 78

Text #14

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1519024 (The Pile)

Max Activating Token Index: 535

Text #15

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1814115 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5636. Min Act: -0.0000

Data Index: 977839 (The Pile)

Max Activating Token Index: 644

Text #17

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5448. Min Act: -0.0000

Data Index: 999628 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5993. Min Act: -0.0000

Data Index: 972075 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5379. Min Act: -0.0000

Data Index: 167714 (The Pile)

Max Activating Token Index: 172