Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2580 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3677. Min Act: -0.0001

Data Index: 785210 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3671. Min Act: -0.0001

Data Index: 710173 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3694. Min Act: -0.0001

Data Index: 1348551 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3591. Min Act: -0.0001

Data Index: 1230982 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3236. Min Act: -0.0001

Data Index: 1260771 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3241. Min Act: -0.0001

Data Index: 227877 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3609. Min Act: -0.0001

Data Index: 192568 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3171. Min Act: -0.0001

Data Index: 659741 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3213. Min Act: -0.0001

Data Index: 349576 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3146. Min Act: -0.0001

Data Index: 1335238 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2984. Min Act: -0.0001

Data Index: 815062 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3011. Min Act: -0.0001

Data Index: 3200 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2811. Min Act: -0.0001

Data Index: 433607 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2824. Min Act: -0.0001

Data Index: 572202 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2728. Min Act: -0.0001

Data Index: 993769 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2719. Min Act: -0.0001

Data Index: 771745 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2616. Min Act: -0.0001

Data Index: 139222 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2773. Min Act: -0.0001

Data Index: 178087 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1298787 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2691. Min Act: -0.0001

Data Index: 576372 (C4 (Web Text))

Max Activating Token Index: 393