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

Dataset: The Pile

Neuron 1000 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: 0.5954. Min Range: -0.5954

Max Act: 0.5954. Min Act: -0.0000

Data Index: 335345 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5433. Min Act: -0.0000

Data Index: 83545 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1721800 (The Pile)

Max Activating Token Index: 598

Text #3

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5354. Min Act: 0.0000

Data Index: 1628482 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4692. Min Act: -0.0000

Data Index: 706143 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1709736 (The Pile)

Max Activating Token Index: 405

Text #6

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4915. Min Act: -0.0000

Data Index: 404942 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4962. Min Act: 0.0000

Data Index: 1726195 (The Pile)

Max Activating Token Index: 890

Text #8

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4756. Min Act: 0.0000

Data Index: 1719702 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1932221 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4675. Min Act: -0.0000

Data Index: 859395 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4762. Min Act: -0.0000

Data Index: 134073 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4658. Min Act: -0.0000

Data Index: 967303 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4423. Min Act: -0.0000

Data Index: 808333 (The Pile)

Max Activating Token Index: 547

Text #14

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1566596 (The Pile)

Max Activating Token Index: 268

Text #15

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1240779 (The Pile)

Max Activating Token Index: 310

Text #16

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4497. Min Act: 0.0000

Data Index: 447231 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4677. Min Act: -0.0000

Data Index: 750117 (The Pile)

Max Activating Token Index: 666

Text #18

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4195. Min Act: -0.0000

Data Index: 297554 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4296. Min Act: -0.0000

Data Index: 443638 (The Pile)

Max Activating Token Index: 965