Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 843 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0743. Min Range: -1.0743

Max Act: 1.0233. Min Act: -0.0000

Data Index: 306727 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 1.0743. Min Range: -1.0743

Max Act: 1.0743. Min Act: -0.0000

Data Index: 865835 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1448482 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.7314. Min Act: -0.0000

Data Index: 824674 (The Pile)

Max Activating Token Index: 672

Text #4

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1609232 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.6894. Min Act: -0.0000

Data Index: 224132 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.6894. Min Act: -0.0000

Data Index: 365951 (The Pile)

Max Activating Token Index: 50

Text #7

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.6913. Min Act: -0.0000

Data Index: 439693 (The Pile)

Max Activating Token Index: 859

Text #8

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1328847 (The Pile)

Max Activating Token Index: 35

Text #9

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1014163 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.6300. Min Act: -0.0000

Data Index: 536288 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.5727. Min Act: -0.0000

Data Index: 379381 (The Pile)

Max Activating Token Index: 202

Text #12

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.5983. Min Act: -0.0000

Data Index: 579504 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1505310 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1791208 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.5555. Min Act: -0.0000

Data Index: 287043 (The Pile)

Max Activating Token Index: 11

Text #16

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1074018 (The Pile)

Max Activating Token Index: 134

Text #17

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.5589. Min Act: -0.0000

Data Index: 254909 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.5535. Min Act: -0.0000

Data Index: 440461 (The Pile)

Max Activating Token Index: 81

Text #19

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1812146 (The Pile)

Max Activating Token Index: 93