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

Dataset: The Pile

Neuron 992 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1518750 (The Pile)

Max Activating Token Index: 319

Text #1

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.9073. Min Act: -0.0000

Data Index: 943147 (The Pile)

Max Activating Token Index: 478

Text #2

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8493. Min Act: -0.0000

Data Index: 649059 (The Pile)

Max Activating Token Index: 910

Text #3

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1329512 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8564. Min Act: -0.0000

Data Index: 276285 (The Pile)

Max Activating Token Index: 526

Text #5

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8090. Min Act: -0.0000

Data Index: 319287 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1353545 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8224. Min Act: -0.0000

Data Index: 398512 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1127449 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1817344 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7962. Min Act: -0.0000

Data Index: 871715 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7911. Min Act: -0.0000

Data Index: 280220 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7648. Min Act: -0.0000

Data Index: 363841 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7562. Min Act: -0.0000

Data Index: 585566 (The Pile)

Max Activating Token Index: 934

Text #14

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7917. Min Act: -0.0000

Data Index: 574406 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1160753 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1997141 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1732559 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1412386 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1209633 (The Pile)

Max Activating Token Index: 331