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

Dataset: The Pile

Neuron 1324 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: 0.8453. Min Range: -0.8453

Max Act: 0.8453. Min Act: -0.0000

Data Index: 219244 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1791786 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1563500 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1792434 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6475. Min Act: -0.0000

Data Index: 170267 (The Pile)

Max Activating Token Index: 877

Text #5

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6405. Min Act: -0.0000

Data Index: 572735 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6289. Min Act: -0.0000

Data Index: 432237 (The Pile)

Max Activating Token Index: 914

Text #7

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6298. Min Act: -0.0000

Data Index: 174866 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1959305 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1637986 (The Pile)

Max Activating Token Index: 331

Text #10

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1936828 (The Pile)

Max Activating Token Index: 390

Text #11

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1501150 (The Pile)

Max Activating Token Index: 914

Text #12

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1168946 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1862418 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6216. Min Act: -0.0000

Data Index: 73880 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6531. Min Act: -0.0000

Data Index: 954833 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1300355 (The Pile)

Max Activating Token Index: 558

Text #17

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1635158 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1010568 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1754348 (The Pile)

Max Activating Token Index: 515