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

Dataset: The Pile

Neuron 1523 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7607. Min Act: -0.0000

Data Index: 768544 (The Pile)

Max Activating Token Index: 287

Text #1

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5815. Min Act: -0.0000

Data Index: 454226 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1417912 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4619. Min Act: -0.0000

Data Index: 409132 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1675812 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4886. Min Act: -0.0000

Data Index: 499742 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4262. Min Act: -0.0000

Data Index: 64511 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4528. Min Act: -0.0000

Data Index: 727159 (The Pile)

Max Activating Token Index: 564

Text #8

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4531. Min Act: -0.0000

Data Index: 665542 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4064. Min Act: -0.0000

Data Index: 613106 (The Pile)

Max Activating Token Index: 118

Text #10

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.3937. Min Act: -0.0000

Data Index: 582371 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1173789 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.3132. Min Act: -0.0000

Data Index: 569340 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1432849 (The Pile)

Max Activating Token Index: 289

Text #14

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.3889. Min Act: -0.0000

Data Index: 604162 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.3147. Min Act: -0.0000

Data Index: 987775 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.3769. Min Act: -0.0000

Data Index: 909583 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.3693. Min Act: -0.0000

Data Index: 185972 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4130. Min Act: -0.0000

Data Index: 320982 (The Pile)

Max Activating Token Index: 28

Text #19

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1040147 (The Pile)

Max Activating Token Index: 903