Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1873 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0894. Min Act: -0.0005

Data Index: 95619 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0680. Min Act: -0.0005

Data Index: 658096 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0699. Min Act: -0.0005

Data Index: 1091303 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0700. Min Act: -0.0005

Data Index: 1007886 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0704. Min Act: -0.0005

Data Index: 744300 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0648. Min Act: -0.0005

Data Index: 1329309 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0702. Min Act: -0.0005

Data Index: 271699 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0651. Min Act: -0.0005

Data Index: 1281596 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0620. Min Act: -0.0005

Data Index: 74209 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0648. Min Act: -0.0005

Data Index: 572805 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0622. Min Act: -0.0005

Data Index: 811091 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0593. Min Act: -0.0005

Data Index: 1145462 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0607. Min Act: -0.0005

Data Index: 409095 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0594. Min Act: -0.0005

Data Index: 374545 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0602. Min Act: -0.0005

Data Index: 1057856 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0539. Min Act: -0.0005

Data Index: 393204 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0593. Min Act: -0.0005

Data Index: 281736 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0566. Min Act: -0.0005

Data Index: 1349205 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0591. Min Act: -0.0005

Data Index: 736829 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0569. Min Act: -0.0005

Data Index: 515943 (C4 (Web Text))

Max Activating Token Index: 243