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

Dataset: The Pile

Neuron 618 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: 1.6079. Min Range: -1.6079

Max Act: 1.6079. Min Act: -0.0000

Data Index: 627886 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.3833. Min Act: -0.0000

Data Index: 412263 (The Pile)

Max Activating Token Index: 245

Text #2

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.5139. Min Act: -0.0000

Data Index: 1104571 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.2453. Min Act: -0.0000

Data Index: 126203 (The Pile)

Max Activating Token Index: 190

Text #4

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.2939. Min Act: -0.0000

Data Index: 299628 (The Pile)

Max Activating Token Index: 281

Text #5

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1031. Min Act: -0.0000

Data Index: 205105 (The Pile)

Max Activating Token Index: 201

Text #6

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1918406 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.2171. Min Act: -0.0000

Data Index: 98820 (The Pile)

Max Activating Token Index: 296

Text #8

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.9649. Min Act: -0.0000

Data Index: 60399 (The Pile)

Max Activating Token Index: 478

Text #9

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0616. Min Act: -0.0000

Data Index: 1048843 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1953. Min Act: -0.0000

Data Index: 1506010 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0698. Min Act: -0.0000

Data Index: 450135 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1354702 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1095. Min Act: -0.0000

Data Index: 691184 (The Pile)

Max Activating Token Index: 169

Text #14

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0331. Min Act: -0.0000

Data Index: 804722 (The Pile)

Max Activating Token Index: 692

Text #15

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1290757 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1300848 (The Pile)

Max Activating Token Index: 310

Text #17

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0099. Min Act: -0.0000

Data Index: 703327 (The Pile)

Max Activating Token Index: 457

Text #18

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1324. Min Act: -0.0000

Data Index: 1832887 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1770722 (The Pile)

Max Activating Token Index: 840