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

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

Neuron 845 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.9643. Min Act: -0.0001

Data Index: 1382691 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.8994. Min Act: -0.0001

Data Index: 1411717 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.8770. Min Act: -0.0001

Data Index: 122894 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.8309. Min Act: -0.0001

Data Index: 106976 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1602589 (Python Code)

Max Activating Token Index: 49

Text #5

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1491600 (Python Code)

Max Activating Token Index: 595

Text #6

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7604. Min Act: -0.0001

Data Index: 861588 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7744. Min Act: -0.0001

Data Index: 1422730 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1652662 (Python Code)

Max Activating Token Index: 193

Text #9

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7615. Min Act: -0.0001

Data Index: 1412967 (Python Code)

Max Activating Token Index: 845

Text #10

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7537. Min Act: -0.0001

Data Index: 1606638 (Python Code)

Max Activating Token Index: 85

Text #11

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6787. Min Act: -0.0001

Data Index: 1536855 (Python Code)

Max Activating Token Index: 203

Text #12

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1593980 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7016. Min Act: -0.0001

Data Index: 1585487 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7165. Min Act: -0.0001

Data Index: 1569566 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6988. Min Act: -0.0001

Data Index: 1455513 (Python Code)

Max Activating Token Index: 800

Text #16

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1611472 (Python Code)

Max Activating Token Index: 773

Text #17

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7046. Min Act: -0.0001

Data Index: 563220 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6982. Min Act: -0.0001

Data Index: 211445 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7135. Min Act: -0.0001

Data Index: 695194 (C4 (Web Text))

Max Activating Token Index: 665