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

Dataset: The Pile

Neuron 3004 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: 0.9976. Min Range: -0.9976

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1205557 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1114642 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9976. Min Act: -0.0000

Data Index: 463645 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9351. Min Act: -0.0000

Data Index: 970398 (The Pile)

Max Activating Token Index: 385

Text #4

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9918. Min Act: -0.0000

Data Index: 631726 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8542. Min Act: -0.0000

Data Index: 1557693 (The Pile)

Max Activating Token Index: 247

Text #6

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8863. Min Act: -0.0000

Data Index: 582489 (The Pile)

Max Activating Token Index: 313

Text #7

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8457. Min Act: -0.0000

Data Index: 34488 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8448. Min Act: -0.0000

Data Index: 386765 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1625591 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8269. Min Act: -0.0000

Data Index: 980618 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8444. Min Act: -0.0000

Data Index: 737044 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1347214 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1659549 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1675542 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7819. Min Act: -0.0000

Data Index: 784210 (The Pile)

Max Activating Token Index: 373

Text #16

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1905534 (The Pile)

Max Activating Token Index: 45

Text #17

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8413. Min Act: -0.0000

Data Index: 270688 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1643104 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1298911 (The Pile)

Max Activating Token Index: 299