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

Dataset: The Pile

Neuron 176 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: 1.9990. Min Range: -1.9990

Max Act: 1.9990. Min Act: -0.0000

Data Index: 23810 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.9638. Min Act: -0.0000

Data Index: 1464302 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.8709. Min Act: -0.0000

Data Index: 1216409 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.7690. Min Act: -0.0000

Data Index: 1573451 (The Pile)

Max Activating Token Index: 56

Text #4

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.8406. Min Act: -0.0000

Data Index: 1154794 (The Pile)

Max Activating Token Index: 641

Text #5

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.7847. Min Act: -0.0000

Data Index: 842247 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.8014. Min Act: -0.0000

Data Index: 1421383 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.6647. Min Act: -0.0000

Data Index: 1063348 (The Pile)

Max Activating Token Index: 313

Text #8

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.5625. Min Act: -0.0000

Data Index: 185694 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.7234. Min Act: -0.0000

Data Index: 1997888 (The Pile)

Max Activating Token Index: 523

Text #10

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1720712 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.6778. Min Act: -0.0000

Data Index: 191869 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.5826. Min Act: -0.0000

Data Index: 511898 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1641067 (The Pile)

Max Activating Token Index: 773

Text #14

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.4878. Min Act: -0.0000

Data Index: 1909714 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1064217 (The Pile)

Max Activating Token Index: 1005

Text #16

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.5593. Min Act: -0.0000

Data Index: 1659214 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.5502. Min Act: -0.0000

Data Index: 492680 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.4356. Min Act: -0.0000

Data Index: 333934 (The Pile)

Max Activating Token Index: 379

Text #19

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.6227. Min Act: -0.0000

Data Index: 1880331 (The Pile)

Max Activating Token Index: 275