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

Dataset: The Pile

Neuron 1838 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: 0.4843. Min Range: -0.4843

Max Act: 0.4098. Min Act: -0.0000

Data Index: 48366 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4256. Min Act: -0.0000

Data Index: 262004 (The Pile)

Max Activating Token Index: 633

Text #2

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1899608 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4540. Min Act: -0.0000

Data Index: 514708 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1665911 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1966350 (The Pile)

Max Activating Token Index: 393

Text #6

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1801067 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4434. Min Act: -0.0000

Data Index: 387777 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4096. Min Act: -0.0000

Data Index: 434965 (The Pile)

Max Activating Token Index: 700

Text #9

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4049. Min Act: -0.0000

Data Index: 184125 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4263. Min Act: -0.0000

Data Index: 174196 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1433590 (The Pile)

Max Activating Token Index: 975

Text #12

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3547. Min Act: -0.0000

Data Index: 1254252 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3485. Min Act: -0.0000

Data Index: 939718 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3591. Min Act: -0.0000

Data Index: 576333 (The Pile)

Max Activating Token Index: 353

Text #15

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1861608 (The Pile)

Max Activating Token Index: 912

Text #16

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1892662 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1964631 (The Pile)

Max Activating Token Index: 100

Text #18

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1169611 (The Pile)

Max Activating Token Index: 352

Text #19

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3729. Min Act: -0.0000

Data Index: 395202 (The Pile)

Max Activating Token Index: 111