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

Dataset: The Pile

Neuron 4148 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0252. Min Range: -1.0252

Max Act: 1.0252. Min Act: -0.0000

Data Index: 1370094 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1563233 (The Pile)

Max Activating Token Index: 770

Text #2

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1871629 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1429919 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.9084. Min Act: -0.0000

Data Index: 87007 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1807299 (The Pile)

Max Activating Token Index: 638

Text #6

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1691069 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1720961 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1317333 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.7027. Min Act: -0.0000

Data Index: 918361 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.7033. Min Act: -0.0000

Data Index: 113535 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6740. Min Act: -0.0000

Data Index: 569436 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1130401 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6802. Min Act: -0.0000

Data Index: 414577 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1207335 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1901213 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6920. Min Act: -0.0000

Data Index: 290306 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1019612 (The Pile)

Max Activating Token Index: 234

Text #18

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6324. Min Act: 0.0000

Data Index: 1666063 (The Pile)

Max Activating Token Index: 680

Text #19

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6596. Min Act: -0.0000

Data Index: 467838 (The Pile)

Max Activating Token Index: 818