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

Dataset: The Pile

Neuron 4043 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.8345. Min Act: -0.0000

Data Index: 1979337 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.4554. Min Act: -0.0000

Data Index: 1973546 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.4402. Min Act: -0.0000

Data Index: 472375 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.2277. Min Act: -0.0000

Data Index: 440121 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.2105. Min Act: -0.0000

Data Index: 1855638 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.1957. Min Act: -0.0000

Data Index: 1861948 (The Pile)

Max Activating Token Index: 255

Text #6

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.9178. Min Act: -0.0000

Data Index: 1429431 (The Pile)

Max Activating Token Index: 207

Text #7

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.8662. Min Act: -0.0000

Data Index: 1514771 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.2454. Min Act: -0.0000

Data Index: 246806 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.6533. Min Act: -0.0000

Data Index: 1042850 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.6899. Min Act: -0.0000

Data Index: 1106944 (The Pile)

Max Activating Token Index: 568

Text #11

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.5694. Min Act: -0.0000

Data Index: 687840 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.6595. Min Act: -0.0000

Data Index: 94562 (The Pile)

Max Activating Token Index: 144

Text #13

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.7539. Min Act: -0.0000

Data Index: 1389415 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.7568. Min Act: -0.0000

Data Index: 860837 (The Pile)

Max Activating Token Index: 308

Text #15

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.7343. Min Act: -0.0000

Data Index: 1057050 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.6054. Min Act: -0.0000

Data Index: 1820452 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.7126. Min Act: -0.0000

Data Index: 767609 (The Pile)

Max Activating Token Index: 678

Text #18

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.7101. Min Act: -0.0000

Data Index: 319306 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 3.8345. Min Range: -3.8345

Max Act: 2.5680. Min Act: -0.0000

Data Index: 1188813 (The Pile)

Max Activating Token Index: 989