Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 519 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0764. Min Act: -0.0002

Data Index: 207740 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0763. Min Act: -0.0002

Data Index: 196948 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0727. Min Act: -0.0000

Data Index: 931449 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0700. Min Act: -0.0001

Data Index: 941183 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0735. Min Act: -0.0002

Data Index: 75090 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1293585 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1178028 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1346846 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1307401 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0619. Min Act: -0.0002

Data Index: 992128 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0636. Min Act: -0.0002

Data Index: 478843 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1237419 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1203855 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1010146 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0616. Min Act: -0.0002

Data Index: 439190 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0642. Min Act: -0.0002

Data Index: 272867 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0613. Min Act: -0.0002

Data Index: 377698 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0611. Min Act: -0.0001

Data Index: 365548 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0608. Min Act: -0.0002

Data Index: 452057 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1072938 (C4 (Web Text))

Max Activating Token Index: 495