Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 843 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0874. Min Act: -0.0001

Data Index: 698214 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0696. Min Act: -0.0002

Data Index: 586841 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0689. Min Act: -0.0002

Data Index: 522103 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0700. Min Act: -0.0002

Data Index: 934009 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0728. Min Act: -0.0002

Data Index: 784264 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0696. Min Act: -0.0002

Data Index: 78513 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1274806 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0624. Min Act: -0.0001

Data Index: 295078 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1257243 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1052683 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0714. Min Act: -0.0002

Data Index: 829812 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0661. Min Act: -0.0002

Data Index: 721159 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0672. Min Act: -0.0001

Data Index: 882109 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0624. Min Act: -0.0001

Data Index: 897903 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0611. Min Act: -0.0002

Data Index: 559628 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0611. Min Act: -0.0002

Data Index: 729164 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0588. Min Act: -0.0002

Data Index: 63209 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1177721 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0615. Min Act: -0.0002

Data Index: 45146 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0670. Min Act: -0.0002

Data Index: 706614 (C4 (Web Text))

Max Activating Token Index: 442