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

Dataset: The Pile

Neuron 3001 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.3480. Min Act: -0.0000

Data Index: 1367134 (The Pile)

Max Activating Token Index: 886

Text #1

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.1824. Min Act: -0.0000

Data Index: 23644 (The Pile)

Max Activating Token Index: 577

Text #2

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1591691 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1507088 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9979. Min Act: -0.0000

Data Index: 970540 (The Pile)

Max Activating Token Index: 516

Text #5

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0698. Min Act: -0.0000

Data Index: 17617 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0426. Min Act: -0.0000

Data Index: 699615 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9752. Min Act: -0.0000

Data Index: 94218 (The Pile)

Max Activating Token Index: 364

Text #8

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1283633 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9585. Min Act: -0.0000

Data Index: 1272262 (The Pile)

Max Activating Token Index: 189

Text #10

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1278277 (The Pile)

Max Activating Token Index: 795

Text #11

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9025. Min Act: -0.0000

Data Index: 513244 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8320. Min Act: -0.0000

Data Index: 267977 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1850967 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9350. Min Act: -0.0000

Data Index: 163702 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1967989 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8555. Min Act: -0.0000

Data Index: 164233 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1107573 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8144. Min Act: -0.0000

Data Index: 334794 (The Pile)

Max Activating Token Index: 270

Text #19

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8649. Min Act: -0.0000

Data Index: 708988 (The Pile)

Max Activating Token Index: 190