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

Dataset: The Pile

Neuron 2129 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: 1.2697. Min Range: -1.2697

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1068119 (The Pile)

Max Activating Token Index: 578

Text #1

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0912. Min Act: -0.0000

Data Index: 1077068 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.1510. Min Act: -0.0000

Data Index: 707857 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0252. Min Act: -0.0000

Data Index: 497688 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1479488 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1589731 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9961. Min Act: -0.0000

Data Index: 440557 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1539966 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8776. Min Act: -0.0000

Data Index: 148502 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1450941 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1758308 (The Pile)

Max Activating Token Index: 973

Text #11

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1941957 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8868. Min Act: -0.0000

Data Index: 170517 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8611. Min Act: -0.0000

Data Index: 549997 (The Pile)

Max Activating Token Index: 289

Text #14

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1540433 (The Pile)

Max Activating Token Index: 279

Text #15

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8406. Min Act: -0.0000

Data Index: 926565 (The Pile)

Max Activating Token Index: 993

Text #16

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8234. Min Act: -0.0000

Data Index: 549774 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1618553 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.7979. Min Act: -0.0000

Data Index: 456177 (The Pile)

Max Activating Token Index: 166

Text #19

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.7595. Min Act: -0.0000

Data Index: 363715 (The Pile)

Max Activating Token Index: 83