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

Dataset: The Pile

Neuron 2320 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3211. Min Range: -1.3211

Max Act: 1.3211. Min Act: -0.0000

Data Index: 1215357 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 1.3211. Min Range: -1.3211

Max Act: 1.1801. Min Act: -0.0000

Data Index: 1458628 (The Pile)

Max Activating Token Index: 698

Text #2

Max Range: 1.3211. Min Range: -1.3211

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1035365 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 1.3211. Min Range: -1.3211

Max Act: 1.1023. Min Act: -0.0000

Data Index: 103505 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 1.3211. Min Range: -1.3211

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1614976 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 1.3211. Min Range: -1.3211

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1858774 (The Pile)

Max Activating Token Index: 690

Text #6

Max Range: 1.3211. Min Range: -1.3211

Max Act: 1.0148. Min Act: -0.0000

Data Index: 677996 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 1.3211. Min Range: -1.3211

Max Act: 1.0192. Min Act: -0.0000

Data Index: 1478869 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 1.3211. Min Range: -1.3211

Max Act: 1.0408. Min Act: -0.0000

Data Index: 580476 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 1.3211. Min Range: -1.3211

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1578815 (The Pile)

Max Activating Token Index: 85

Text #10

Max Range: 1.3211. Min Range: -1.3211

Max Act: 1.0130. Min Act: -0.0000

Data Index: 1527220 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 1.3211. Min Range: -1.3211

Max Act: 0.9990. Min Act: -0.0000

Data Index: 596119 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 1.3211. Min Range: -1.3211

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1048481 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 1.3211. Min Range: -1.3211

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1947253 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 1.3211. Min Range: -1.3211

Max Act: 0.9941. Min Act: -0.0000

Data Index: 530040 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 1.3211. Min Range: -1.3211

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1633956 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 1.3211. Min Range: -1.3211

Max Act: 0.9379. Min Act: -0.0000

Data Index: 630004 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 1.3211. Min Range: -1.3211

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1802858 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 1.3211. Min Range: -1.3211

Max Act: 0.9291. Min Act: -0.0000

Data Index: 12433 (The Pile)

Max Activating Token Index: 472

Text #19

Max Range: 1.3211. Min Range: -1.3211

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1705448 (The Pile)

Max Activating Token Index: 354