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

Dataset: The Pile

Neuron 4885 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: 1.9099. Min Range: -1.9099

Max Act: 1.9099. Min Act: -0.0000

Data Index: 326363 (The Pile)

Max Activating Token Index: 773

Text #1

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.6978. Min Act: -0.0000

Data Index: 1889041 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1348177 (The Pile)

Max Activating Token Index: 513

Text #3

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.7511. Min Act: -0.0000

Data Index: 1877160 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.7461. Min Act: -0.0000

Data Index: 1912327 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.5695. Min Act: -0.0000

Data Index: 396992 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.6479. Min Act: -0.0000

Data Index: 1898554 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.6412. Min Act: -0.0000

Data Index: 367831 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.6222. Min Act: -0.0000

Data Index: 1520910 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.5258. Min Act: -0.0000

Data Index: 494610 (The Pile)

Max Activating Token Index: 512

Text #10

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1008684 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.7120. Min Act: -0.0000

Data Index: 1426783 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.5797. Min Act: -0.0000

Data Index: 1741770 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.5680. Min Act: -0.0000

Data Index: 57295 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.5632. Min Act: -0.0000

Data Index: 297850 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.5637. Min Act: -0.0000

Data Index: 1317692 (The Pile)

Max Activating Token Index: 170

Text #16

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.5491. Min Act: -0.0000

Data Index: 665143 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1897428 (The Pile)

Max Activating Token Index: 850

Text #18

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.5160. Min Act: -0.0000

Data Index: 1064400 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.5096. Min Act: -0.0000

Data Index: 882459 (The Pile)

Max Activating Token Index: 887