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

Dataset: The Pile

Neuron 532 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: 1.3917. Min Range: -1.3917

Max Act: 1.3917. Min Act: -0.0000

Data Index: 1212071 (The Pile)

Max Activating Token Index: 676

Text #1

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.1618. Min Act: -0.0000

Data Index: 1276693 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.0772. Min Act: -0.0000

Data Index: 271404 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1507723 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8089. Min Act: -0.0000

Data Index: 796026 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.0649. Min Act: -0.0000

Data Index: 622781 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1945313 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9642. Min Act: -0.0000

Data Index: 146087 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9925. Min Act: -0.0000

Data Index: 838799 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1397638 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1861461 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.0253. Min Act: -0.0000

Data Index: 647975 (The Pile)

Max Activating Token Index: 618

Text #12

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8739. Min Act: -0.0000

Data Index: 996949 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1061911 (The Pile)

Max Activating Token Index: 569

Text #14

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.7474. Min Act: -0.0000

Data Index: 1455515 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.7651. Min Act: -0.0000

Data Index: 791390 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1632840 (The Pile)

Max Activating Token Index: 364

Text #17

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1050790 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8136. Min Act: 0.0000

Data Index: 950517 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.7807. Min Act: -0.0000

Data Index: 119641 (The Pile)

Max Activating Token Index: 221