Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3939 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4840. Min Act: -0.0001

Data Index: 468769 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4344. Min Act: -0.0001

Data Index: 706264 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4404. Min Act: -0.0001

Data Index: 140013 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3811. Min Act: -0.0001

Data Index: 502801 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3953. Min Act: -0.0000

Data Index: 5764 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3771. Min Act: -0.0001

Data Index: 870469 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3740. Min Act: -0.0000

Data Index: 702429 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1210990 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1166802 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3648. Min Act: -0.0001

Data Index: 1062174 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3616. Min Act: -0.0001

Data Index: 416810 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3443. Min Act: -0.0001

Data Index: 958233 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3511. Min Act: -0.0000

Data Index: 503459 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3403. Min Act: -0.0000

Data Index: 844205 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3405. Min Act: -0.0001

Data Index: 250834 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3180. Min Act: -0.0001

Data Index: 795357 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3401. Min Act: -0.0001

Data Index: 315003 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3734. Min Act: -0.0001

Data Index: 826271 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3383. Min Act: -0.0001

Data Index: 572429 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3283. Min Act: -0.0001

Data Index: 84164 (C4 (Web Text))

Max Activating Token Index: 598