Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 598 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1572. Min Act: -0.0003

Data Index: 636369 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1000. Min Act: -0.0003

Data Index: 1182508 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0985. Min Act: -0.0003

Data Index: 397994 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1028. Min Act: -0.0003

Data Index: 553351 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1039. Min Act: -0.0003

Data Index: 458860 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0947. Min Act: -0.0003

Data Index: 184624 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0920. Min Act: -0.0003

Data Index: 1222591 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0898. Min Act: -0.0003

Data Index: 1115625 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0873. Min Act: -0.0003

Data Index: 932274 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0886. Min Act: -0.0003

Data Index: 462406 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0886. Min Act: -0.0003

Data Index: 133365 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0867. Min Act: -0.0003

Data Index: 1226537 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0886. Min Act: -0.0003

Data Index: 474669 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0870. Min Act: -0.0003

Data Index: 721136 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1250897 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0883. Min Act: -0.0003

Data Index: 256507 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0840. Min Act: -0.0003

Data Index: 610791 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0828. Min Act: -0.0003

Data Index: 230381 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0848. Min Act: -0.0003

Data Index: 275798 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0845. Min Act: -0.0003

Data Index: 991468 (C4 (Web Text))

Max Activating Token Index: 49