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

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

Neuron 2107 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9857. Min Range: -3.9857

Max Act: 3.9857. Min Act: -0.0001

Data Index: 533372 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 3.9857. Min Range: -3.9857

Max Act: 3.3452. Min Act: -0.0000

Data Index: 844027 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 3.9857. Min Range: -3.9857

Max Act: 3.4945. Min Act: -0.0001

Data Index: 357936 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 3.9857. Min Range: -3.9857

Max Act: 3.3746. Min Act: -0.0000

Data Index: 424342 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 3.9857. Min Range: -3.9857

Max Act: 3.1928. Min Act: -0.0000

Data Index: 1293453 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.8693. Min Act: -0.0001

Data Index: 958903 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.5657. Min Act: -0.0001

Data Index: 254237 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.7698. Min Act: -0.0001

Data Index: 157385 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.6422. Min Act: -0.0001

Data Index: 561865 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.6751. Min Act: -0.0000

Data Index: 1156458 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.6564. Min Act: -0.0000

Data Index: 295720 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.4316. Min Act: -0.0000

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.6846. Min Act: -0.0001

Data Index: 1276060 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.6935. Min Act: -0.0000

Data Index: 788970 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.5369. Min Act: -0.0001

Data Index: 1264415 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.6544. Min Act: -0.0001

Data Index: 1218658 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.4421. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.4145. Min Act: -0.0000

Data Index: 788049 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.5297. Min Act: -0.0000

Data Index: 805170 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 3.9857. Min Range: -3.9857

Max Act: 2.2818. Min Act: -0.0001

Data Index: 584393 (C4 (Web Text))

Max Activating Token Index: 642