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

Dataset: The Pile

Neuron 3672 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: 1.7421. Min Range: -1.7421

Max Act: 1.7421. Min Act: -0.0000

Data Index: 1993226 (The Pile)

Max Activating Token Index: 423

Text #1

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.4444. Min Act: -0.0000

Data Index: 1098982 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.5151. Min Act: -0.0000

Data Index: 1952985 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.3342. Min Act: -0.0000

Data Index: 363338 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.3950. Min Act: -0.0000

Data Index: 411705 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.2848. Min Act: -0.0000

Data Index: 404928 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.0595. Min Act: -0.0000

Data Index: 803271 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.2011. Min Act: -0.0000

Data Index: 115206 (The Pile)

Max Activating Token Index: 251

Text #8

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.1117. Min Act: -0.0000

Data Index: 822727 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.0984. Min Act: -0.0000

Data Index: 1933048 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1542875 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 1.7421. Min Range: -1.7421

Max Act: 0.9769. Min Act: -0.0000

Data Index: 1235164 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 1.7421. Min Range: -1.7421

Max Act: 0.9799. Min Act: -0.0000

Data Index: 643632 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 1.7421. Min Range: -1.7421

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1356149 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1967529 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 1.7421. Min Range: -1.7421

Max Act: 0.8992. Min Act: -0.0000

Data Index: 880676 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 1.7421. Min Range: -1.7421

Max Act: 0.9972. Min Act: -0.0000

Data Index: 343473 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 1.7421. Min Range: -1.7421

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1501935 (The Pile)

Max Activating Token Index: 548

Text #18

Max Range: 1.7421. Min Range: -1.7421

Max Act: 0.9151. Min Act: -0.0000

Data Index: 561750 (The Pile)

Max Activating Token Index: 426

Text #19

Max Range: 1.7421. Min Range: -1.7421

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1045552 (The Pile)

Max Activating Token Index: 419