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

Dataset: The Pile

Neuron 1307 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: 0.8269. Min Range: -0.8269

Max Act: 0.7974. Min Act: -0.0000

Data Index: 872970 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.8269. Min Act: -0.0000

Data Index: 465492 (The Pile)

Max Activating Token Index: 264

Text #2

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1105585 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7691. Min Act: -0.0000

Data Index: 264836 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7435. Min Act: -0.0000

Data Index: 769617 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1561168 (The Pile)

Max Activating Token Index: 863

Text #6

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1125484 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1741910 (The Pile)

Max Activating Token Index: 338

Text #8

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1611874 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1591515 (The Pile)

Max Activating Token Index: 998

Text #10

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7107. Min Act: -0.0000

Data Index: 255419 (The Pile)

Max Activating Token Index: 974

Text #11

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6791. Min Act: -0.0000

Data Index: 592890 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6648. Min Act: -0.0000

Data Index: 369505 (The Pile)

Max Activating Token Index: 999

Text #13

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6540. Min Act: -0.0000

Data Index: 867538 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6572. Min Act: -0.0000

Data Index: 739992 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6426. Min Act: -0.0000

Data Index: 86431 (The Pile)

Max Activating Token Index: 866

Text #16

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6925. Min Act: -0.0000

Data Index: 528921 (The Pile)

Max Activating Token Index: 884

Text #17

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1848461 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1179713 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1539224 (The Pile)

Max Activating Token Index: 956