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

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

Neuron 4546 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0618. Min Act: -0.0002

Data Index: 609779 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0586. Min Act: -0.0002

Data Index: 317360 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0595. Min Act: -0.0002

Data Index: 767392 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0563. Min Act: -0.0002

Data Index: 879443 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0562. Min Act: -0.0002

Data Index: 816392 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0511. Min Act: -0.0002

Data Index: 667130 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0555. Min Act: -0.0002

Data Index: 402860 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0550. Min Act: -0.0002

Data Index: 746713 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0501. Min Act: -0.0002

Data Index: 121361 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0544. Min Act: -0.0002

Data Index: 138005 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0509. Min Act: -0.0002

Data Index: 244940 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0492. Min Act: -0.0002

Data Index: 376450 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1315381 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1128980 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0529. Min Act: -0.0002

Data Index: 522992 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0470. Min Act: -0.0002

Data Index: 353600 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1140176 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0514. Min Act: -0.0002

Data Index: 403489 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0500. Min Act: -0.0002

Data Index: 388863 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1049780 (C4 (Web Text))

Max Activating Token Index: 265