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

Dataset: The Pile

Neuron 4174 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: 0.7343. Min Range: -0.7343

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1161921 (The Pile)

Max Activating Token Index: 891

Text #1

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6552. Min Act: -0.0000

Data Index: 488321 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5885. Min Act: -0.0000

Data Index: 860293 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1028184 (The Pile)

Max Activating Token Index: 509

Text #4

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5288. Min Act: -0.0000

Data Index: 742006 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5571. Min Act: -0.0000

Data Index: 52398 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5317. Min Act: -0.0000

Data Index: 397217 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1135591 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1130649 (The Pile)

Max Activating Token Index: 612

Text #9

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4909. Min Act: -0.0000

Data Index: 203886 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5059. Min Act: -0.0000

Data Index: 266478 (The Pile)

Max Activating Token Index: 591

Text #11

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4452. Min Act: -0.0000

Data Index: 647533 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1181763 (The Pile)

Max Activating Token Index: 986

Text #13

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1480241 (The Pile)

Max Activating Token Index: 984

Text #14

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1212763 (The Pile)

Max Activating Token Index: 153

Text #15

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1395614 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1381991 (The Pile)

Max Activating Token Index: 561

Text #17

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1260578 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4370. Min Act: -0.0000

Data Index: 659572 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4061. Min Act: -0.0000

Data Index: 343 (The Pile)

Max Activating Token Index: 634