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

Dataset: The Pile

Neuron 303 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1779510 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1603475 (The Pile)

Max Activating Token Index: 689

Text #2

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1107726 (The Pile)

Max Activating Token Index: 563

Text #3

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7072. Min Act: -0.0000

Data Index: 735156 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1377139 (The Pile)

Max Activating Token Index: 307

Text #5

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1658961 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1854152 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1746458 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6131. Min Act: -0.0000

Data Index: 196129 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1528697 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1806401 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1956187 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1687955 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5372. Min Act: -0.0000

Data Index: 209079 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1753555 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5162. Min Act: -0.0000

Data Index: 236594 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.4790. Min Act: -0.0000

Data Index: 990383 (The Pile)

Max Activating Token Index: 881

Text #17

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1928107 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1429269 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5014. Min Act: -0.0000

Data Index: 865419 (The Pile)

Max Activating Token Index: 176