Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4714 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0000

Data Index: 805924 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0714. Min Act: -0.0000

Data Index: 410932 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0600. Min Act: -0.0000

Data Index: 568953 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0668. Min Act: -0.0000

Data Index: 233083 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1103108 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0612. Min Act: -0.0000

Data Index: 449492 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0562. Min Act: -0.0000

Data Index: 437114 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0533. Min Act: -0.0000

Data Index: 567640 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0586. Min Act: -0.0000

Data Index: 978359 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1124372 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0559. Min Act: -0.0000

Data Index: 886793 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0532. Min Act: -0.0000

Data Index: 428908 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0550. Min Act: -0.0000

Data Index: 27865 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0568. Min Act: -0.0000

Data Index: 132870 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0533. Min Act: -0.0000

Data Index: 1222987 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0536. Min Act: -0.0000

Data Index: 337590 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0537. Min Act: -0.0000

Data Index: 106719 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0531. Min Act: -0.0000

Data Index: 1249005 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0530. Min Act: -0.0000

Data Index: 402865 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0530. Min Act: -0.0000

Data Index: 1170978 (C4 (Web Text))

Max Activating Token Index: 375