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

Dataset: The Pile

Neuron 2020 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: 0.3357. Min Range: -0.3357

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1898447 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1445195 (The Pile)

Max Activating Token Index: 821

Text #2

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1370807 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3214. Min Act: -0.0000

Data Index: 303163 (The Pile)

Max Activating Token Index: 380

Text #4

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3353. Min Act: -0.0000

Data Index: 123304 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1577954 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3357. Min Act: -0.0000

Data Index: 185358 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2767. Min Act: -0.0000

Data Index: 462202 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1800411 (The Pile)

Max Activating Token Index: 565

Text #9

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2792. Min Act: -0.0000

Data Index: 49714 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1102998 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1132749 (The Pile)

Max Activating Token Index: 445

Text #12

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2837. Min Act: -0.0000

Data Index: 513056 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1293526 (The Pile)

Max Activating Token Index: 348

Text #14

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3031. Min Act: -0.0000

Data Index: 407190 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2617. Min Act: -0.0000

Data Index: 723188 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1654359 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1540240 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1323464 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2804. Min Act: -0.0000

Data Index: 572119 (The Pile)

Max Activating Token Index: 384