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

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

Neuron 602 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0002

Data Index: 242586 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0889. Min Act: -0.0002

Data Index: 630615 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0867. Min Act: -0.0002

Data Index: 813839 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0781. Min Act: -0.0002

Data Index: 315988 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1156141 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1250426 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0698. Min Act: -0.0002

Data Index: 214823 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0699. Min Act: -0.0002

Data Index: 996432 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0704. Min Act: -0.0002

Data Index: 485691 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0682. Min Act: -0.0002

Data Index: 339108 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0696. Min Act: -0.0002

Data Index: 499888 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0702. Min Act: -0.0002

Data Index: 144144 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0686. Min Act: -0.0002

Data Index: 498361 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1078681 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1119076 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0659. Min Act: -0.0002

Data Index: 782588 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1289489 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0663. Min Act: -0.0002

Data Index: 55880 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1156140 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0662. Min Act: -0.0002

Data Index: 771376 (C4 (Web Text))

Max Activating Token Index: 250