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

Dataset: The Pile

Neuron 1984 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: 0.7763. Min Range: -0.7763

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1704473 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.7371. Min Act: -0.0000

Data Index: 1990483 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.7427. Min Act: -0.0000

Data Index: 535767 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1332345 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1713173 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.7662. Min Act: -0.0000

Data Index: 202901 (The Pile)

Max Activating Token Index: 33

Text #6

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6985. Min Act: -0.0000

Data Index: 66358 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.7159. Min Act: -0.0000

Data Index: 561879 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1416429 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1468148 (The Pile)

Max Activating Token Index: 529

Text #10

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1145577 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.7063. Min Act: -0.0000

Data Index: 114603 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1297134 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1283201 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1517541 (The Pile)

Max Activating Token Index: 844

Text #15

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1190727 (The Pile)

Max Activating Token Index: 303

Text #16

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.7010. Min Act: -0.0000

Data Index: 959469 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6956. Min Act: -0.0000

Data Index: 911314 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1802573 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6937. Min Act: -0.0000

Data Index: 420753 (The Pile)

Max Activating Token Index: 860