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

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

Neuron 4405 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: 0.9799. Min Range: -0.9799

Max Act: 0.9546. Min Act: -0.0000

Data Index: 263908 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9799. Min Act: -0.0000

Data Index: 818605 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9613. Min Act: -0.0000

Data Index: 343478 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9435. Min Act: -0.0000

Data Index: 736020 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9773. Min Act: -0.0000

Data Index: 780602 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9149. Min Act: -0.0000

Data Index: 460766 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8361. Min Act: -0.0000

Data Index: 994222 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8747. Min Act: -0.0000

Data Index: 543184 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8207. Min Act: -0.0000

Data Index: 648478 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7656. Min Act: -0.0000

Data Index: 891527 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8148. Min Act: -0.0000

Data Index: 8199 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8583. Min Act: -0.0000

Data Index: 29916 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7753. Min Act: -0.0000

Data Index: 111928 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7934. Min Act: -0.0000

Data Index: 639377 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1262086 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8357. Min Act: -0.0000

Data Index: 495547 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7123. Min Act: -0.0000

Data Index: 216788 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7199. Min Act: -0.0000

Data Index: 476528 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1161409 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7670. Min Act: -0.0000

Data Index: 565237 (C4 (Web Text))

Max Activating Token Index: 259