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

Dataset: The Pile

Neuron 4039 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: 1.0101. Min Range: -1.0101

Max Act: 1.0101. Min Act: -0.0000

Data Index: 390 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.9654. Min Act: -0.0000

Data Index: 308514 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1437055 (The Pile)

Max Activating Token Index: 320

Text #3

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8685. Min Act: -0.0000

Data Index: 695958 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1706040 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8409. Min Act: -0.0000

Data Index: 47598 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1513028 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1039011 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.9262. Min Act: -0.0000

Data Index: 170041 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1091679 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1607639 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1318334 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1783215 (The Pile)

Max Activating Token Index: 615

Text #13

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8040. Min Act: -0.0000

Data Index: 789278 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7432. Min Act: -0.0000

Data Index: 771340 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1368386 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1145779 (The Pile)

Max Activating Token Index: 637

Text #17

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7838. Min Act: -0.0000

Data Index: 1890366 (The Pile)

Max Activating Token Index: 275

Text #18

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7834. Min Act: -0.0000

Data Index: 548886 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1381826 (The Pile)

Max Activating Token Index: 342