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

Dataset: The Pile

Neuron 1426 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.6589. Min Act: -0.0000

Data Index: 715907 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1432511 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5911. Min Act: -0.0000

Data Index: 849769 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5561. Min Act: -0.0000

Data Index: 439385 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1583332 (The Pile)

Max Activating Token Index: 121

Text #5

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1229084 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4858. Min Act: -0.0000

Data Index: 163493 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4832. Min Act: -0.0000

Data Index: 516846 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1395197 (The Pile)

Max Activating Token Index: 328

Text #9

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1619925 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4530. Min Act: -0.0000

Data Index: 379255 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1388774 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1865285 (The Pile)

Max Activating Token Index: 63

Text #13

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4602. Min Act: -0.0000

Data Index: 862192 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1866316 (The Pile)

Max Activating Token Index: 824

Text #15

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1915091 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1799571 (The Pile)

Max Activating Token Index: 596

Text #17

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4552. Min Act: -0.0000

Data Index: 280071 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1388654 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1729833 (The Pile)

Max Activating Token Index: 747