Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1972 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0715. Min Act: -0.0003

Data Index: 1127962 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0712. Min Act: -0.0003

Data Index: 774310 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0003

Data Index: 7395 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0670. Min Act: -0.0003

Data Index: 217955 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1002393 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0648. Min Act: -0.0003

Data Index: 621941 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1198339 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0630. Min Act: -0.0003

Data Index: 752854 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0631. Min Act: -0.0003

Data Index: 411765 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0640. Min Act: -0.0003

Data Index: 1249047 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0629. Min Act: -0.0003

Data Index: 906740 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0628. Min Act: -0.0004

Data Index: 1196053 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1157901 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0620. Min Act: -0.0003

Data Index: 578906 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0606. Min Act: -0.0002

Data Index: 319903 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0618. Min Act: -0.0003

Data Index: 40594 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0616. Min Act: -0.0003

Data Index: 317731 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0595. Min Act: -0.0003

Data Index: 831434 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0587. Min Act: -0.0002

Data Index: 903194 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0593. Min Act: -0.0003

Data Index: 948904 (C4 (Web Text))

Max Activating Token Index: 283