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

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

Neuron 742 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0644. Min Act: -0.0001

Data Index: 290749 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1343396 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1564962 (Python Code)

Max Activating Token Index: 548

Text #3

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0543. Min Act: -0.0001

Data Index: 950776 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0542. Min Act: -0.0001

Data Index: 269679 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0521. Min Act: -0.0001

Data Index: 296941 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0558. Min Act: -0.0001

Data Index: 76111 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1093823 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0581. Min Act: -0.0001

Data Index: 920224 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0555. Min Act: -0.0001

Data Index: 107194 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0551. Min Act: -0.0001

Data Index: 270580 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0535. Min Act: -0.0001

Data Index: 330596 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0538. Min Act: -0.0001

Data Index: 448399 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0535. Min Act: -0.0001

Data Index: 794339 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0524. Min Act: -0.0001

Data Index: 130595 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1633433 (Python Code)

Max Activating Token Index: 451

Text #16

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1072639 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0529. Min Act: -0.0001

Data Index: 94817 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1576218 (Python Code)

Max Activating Token Index: 247

Text #19

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0539. Min Act: -0.0001

Data Index: 816552 (C4 (Web Text))

Max Activating Token Index: 485