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

Dataset: The Pile

Neuron 3983 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: 0.7904. Min Range: -0.7904

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1696861 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1863561 (The Pile)

Max Activating Token Index: 322

Text #2

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7577. Min Act: -0.0000

Data Index: 541221 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7498. Min Act: -0.0000

Data Index: 890813 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1898014 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7478. Min Act: -0.0000

Data Index: 671768 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7357. Min Act: -0.0000

Data Index: 20631 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1023283 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1371343 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6598. Min Act: -0.0000

Data Index: 997617 (The Pile)

Max Activating Token Index: 704

Text #10

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1256565 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6864. Min Act: -0.0000

Data Index: 357066 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1540567 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1114368 (The Pile)

Max Activating Token Index: 402

Text #14

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6373. Min Act: -0.0000

Data Index: 245038 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6414. Min Act: -0.0000

Data Index: 336074 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1229729 (The Pile)

Max Activating Token Index: 323

Text #17

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1429208 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6489. Min Act: -0.0000

Data Index: 558067 (The Pile)

Max Activating Token Index: 133

Text #19

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1778169 (The Pile)

Max Activating Token Index: 477