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

Dataset: The Pile

Neuron 2114 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9562. Min Range: -3.9562

Max Act: 3.9562. Min Act: -0.0000

Data Index: 1354967 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 3.9562. Min Range: -3.9562

Max Act: 3.4986. Min Act: -0.0000

Data Index: 329411 (The Pile)

Max Activating Token Index: 484

Text #2

Max Range: 3.9562. Min Range: -3.9562

Max Act: 3.4162. Min Act: -0.0000

Data Index: 1461882 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 3.9562. Min Range: -3.9562

Max Act: 3.1465. Min Act: -0.0000

Data Index: 37926 (The Pile)

Max Activating Token Index: 594

Text #4

Max Range: 3.9562. Min Range: -3.9562

Max Act: 3.2813. Min Act: -0.0000

Data Index: 106980 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 3.9562. Min Range: -3.9562

Max Act: 3.0029. Min Act: -0.0000

Data Index: 1586464 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.8051. Min Act: -0.0000

Data Index: 929683 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 3.9562. Min Range: -3.9562

Max Act: 3.2003. Min Act: -0.0000

Data Index: 5052 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.8276. Min Act: -0.0000

Data Index: 197121 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.7056. Min Act: -0.0000

Data Index: 457316 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.9722. Min Act: -0.0000

Data Index: 710951 (The Pile)

Max Activating Token Index: 269

Text #11

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.7423. Min Act: -0.0000

Data Index: 293401 (The Pile)

Max Activating Token Index: 759

Text #12

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.5884. Min Act: -0.0000

Data Index: 466384 (The Pile)

Max Activating Token Index: 418

Text #13

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.6010. Min Act: -0.0000

Data Index: 761789 (The Pile)

Max Activating Token Index: 515

Text #14

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.5534. Min Act: -0.0000

Data Index: 1845529 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.6675. Min Act: -0.0000

Data Index: 233282 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.6291. Min Act: -0.0000

Data Index: 277774 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.6248. Min Act: -0.0000

Data Index: 1389173 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.6032. Min Act: -0.0000

Data Index: 333443 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 3.9562. Min Range: -3.9562

Max Act: 2.4626. Min Act: -0.0000

Data Index: 1974345 (The Pile)

Max Activating Token Index: 415