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

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

Neuron 4281 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0862. Min Act: -0.0002

Data Index: 964418 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0801. Min Act: -0.0003

Data Index: 1069260 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0728. Min Act: -0.0003

Data Index: 800845 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0683. Min Act: -0.0003

Data Index: 280951 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0675. Min Act: -0.0003

Data Index: 235318 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0655. Min Act: -0.0003

Data Index: 359544 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1125156 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0639. Min Act: -0.0003

Data Index: 586384 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0649. Min Act: -0.0002

Data Index: 773213 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1106863 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1272735 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0668. Min Act: -0.0003

Data Index: 249412 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0652. Min Act: -0.0003

Data Index: 94630 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0639. Min Act: -0.0003

Data Index: 830426 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0638. Min Act: -0.0003

Data Index: 893188 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0603. Min Act: -0.0003

Data Index: 451840 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0629. Min Act: -0.0003

Data Index: 178700 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0621. Min Act: -0.0002

Data Index: 679471 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0598. Min Act: -0.0003

Data Index: 605177 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0613. Min Act: -0.0003

Data Index: 332883 (C4 (Web Text))

Max Activating Token Index: 824