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

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

Neuron 37 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: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0003

Data Index: 838119 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1285457 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0688. Min Act: -0.0003

Data Index: 975672 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0702. Min Act: -0.0003

Data Index: 279462 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1051672 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0677. Min Act: -0.0004

Data Index: 111188 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0656. Min Act: -0.0002

Data Index: 537475 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0630. Min Act: -0.0004

Data Index: 972824 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0636. Min Act: -0.0003

Data Index: 63393 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1006594 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0615. Min Act: -0.0004

Data Index: 1356396 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1267233 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0628. Min Act: -0.0002

Data Index: 229018 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0629. Min Act: -0.0002

Data Index: 121530 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0641. Min Act: -0.0004

Data Index: 1237769 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0637. Min Act: -0.0003

Data Index: 357201 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1121579 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1353024 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1213139 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0618. Min Act: -0.0003

Data Index: 555744 (C4 (Web Text))

Max Activating Token Index: 985