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

Dataset: The Pile

Neuron 4326 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3663. Min Range: -1.3663

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1639365 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 1.3663. Min Range: -1.3663

Max Act: 1.3663. Min Act: -0.0000

Data Index: 828477 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 1.3663. Min Range: -1.3663

Max Act: 1.1276. Min Act: -0.0000

Data Index: 11556 (The Pile)

Max Activating Token Index: 320

Text #3

Max Range: 1.3663. Min Range: -1.3663

Max Act: 1.2662. Min Act: -0.0000

Data Index: 1786550 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 1.3663. Min Range: -1.3663

Max Act: 1.2023. Min Act: -0.0000

Data Index: 205810 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 1.3663. Min Range: -1.3663

Max Act: 1.0169. Min Act: -0.0000

Data Index: 578416 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1962630 (The Pile)

Max Activating Token Index: 231

Text #7

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1386120 (The Pile)

Max Activating Token Index: 511

Text #8

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1022852 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.9252. Min Act: -0.0000

Data Index: 627612 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1319156 (The Pile)

Max Activating Token Index: 140

Text #11

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8564. Min Act: -0.0000

Data Index: 986359 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.7303. Min Act: -0.0000

Data Index: 619831 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1631242 (The Pile)

Max Activating Token Index: 218

Text #14

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8155. Min Act: -0.0000

Data Index: 648484 (The Pile)

Max Activating Token Index: 529

Text #15

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1914054 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1361151 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8063. Min Act: -0.0000

Data Index: 942776 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8025. Min Act: 0.0000

Data Index: 953226 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1393922 (The Pile)

Max Activating Token Index: 380