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

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

Neuron 2919 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1307510 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1803. Min Act: -0.0000

Data Index: 875844 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1720. Min Act: -0.0001

Data Index: 851060 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1683. Min Act: -0.0001

Data Index: 482540 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1746. Min Act: -0.0001

Data Index: 754588 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1723. Min Act: -0.0001

Data Index: 1054592 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1604. Min Act: -0.0001

Data Index: 820916 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1560. Min Act: -0.0001

Data Index: 603617 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1593. Min Act: -0.0001

Data Index: 82194 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1588. Min Act: -0.0001

Data Index: 632590 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1586. Min Act: -0.0001

Data Index: 879670 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1064439 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1163922 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1535. Min Act: -0.0001

Data Index: 493450 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1541. Min Act: -0.0001

Data Index: 1097010 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1535. Min Act: -0.0001

Data Index: 461405 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1333664 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1523. Min Act: -0.0001

Data Index: 544137 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1515. Min Act: -0.0001

Data Index: 171261 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1389. Min Act: -0.0000

Data Index: 461596 (C4 (Web Text))

Max Activating Token Index: 331