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

Dataset: The Pile

Neuron 2371 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: 1.9596. Min Range: -1.9596

Max Act: 1.9047. Min Act: -0.0000

Data Index: 263087 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.7786. Min Act: -0.0000

Data Index: 1441798 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.7654. Min Act: -0.0000

Data Index: 1361668 (The Pile)

Max Activating Token Index: 494

Text #3

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.9596. Min Act: -0.0000

Data Index: 912612 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.8083. Min Act: -0.0000

Data Index: 157629 (The Pile)

Max Activating Token Index: 382

Text #5

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.7675. Min Act: -0.0000

Data Index: 1630537 (The Pile)

Max Activating Token Index: 250

Text #6

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.7810. Min Act: -0.0000

Data Index: 1904047 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.7437. Min Act: -0.0000

Data Index: 1863985 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.8016. Min Act: -0.0000

Data Index: 77552 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.5753. Min Act: -0.0000

Data Index: 1891683 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.5600. Min Act: -0.0000

Data Index: 1018241 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.5576. Min Act: -0.0000

Data Index: 1203142 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.5381. Min Act: -0.0000

Data Index: 207520 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.4717. Min Act: -0.0000

Data Index: 153538 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.6753. Min Act: -0.0000

Data Index: 860085 (The Pile)

Max Activating Token Index: 397

Text #15

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.4892. Min Act: -0.0000

Data Index: 1079975 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.5652. Min Act: -0.0000

Data Index: 1439037 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.5736. Min Act: -0.0000

Data Index: 926081 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.4923. Min Act: -0.0000

Data Index: 1067451 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.5521. Min Act: -0.0000

Data Index: 1866852 (The Pile)

Max Activating Token Index: 446