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

Dataset: The Pile

Neuron 4378 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.3793. Min Act: -0.0000

Data Index: 1026012 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.5380. Min Act: -0.0000

Data Index: 1574458 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1280945 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.2153. Min Act: -0.0000

Data Index: 428201 (The Pile)

Max Activating Token Index: 845

Text #4

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1354682 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1039922 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.1070. Min Act: -0.0000

Data Index: 824836 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.1503. Min Act: -0.0000

Data Index: 1292446 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1499038 (The Pile)

Max Activating Token Index: 365

Text #9

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1125301 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.9921. Min Act: -0.0000

Data Index: 1734390 (The Pile)

Max Activating Token Index: 329

Text #11

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.0449. Min Act: -0.0000

Data Index: 923549 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.0358. Min Act: -0.0000

Data Index: 616341 (The Pile)

Max Activating Token Index: 130

Text #13

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1131801 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1338210 (The Pile)

Max Activating Token Index: 394

Text #15

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.9566. Min Act: -0.0000

Data Index: 3788 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.9600. Min Act: -0.0000

Data Index: 396696 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1642065 (The Pile)

Max Activating Token Index: 369

Text #18

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1049613 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.0238. Min Act: -0.0000

Data Index: 156500 (The Pile)

Max Activating Token Index: 478