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

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

Neuron 20 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4737. Min Act: -0.0003

Data Index: 320769 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4244. Min Act: -0.0003

Data Index: 921214 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3810. Min Act: -0.0003

Data Index: 675917 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3855. Min Act: -0.0003

Data Index: 1222307 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3726. Min Act: -0.0003

Data Index: 612552 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3813. Min Act: -0.0003

Data Index: 451646 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3811. Min Act: -0.0003

Data Index: 1192958 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3644. Min Act: -0.0003

Data Index: 35744 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3300. Min Act: -0.0003

Data Index: 1264117 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3444. Min Act: -0.0003

Data Index: 733643 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3572. Min Act: -0.0003

Data Index: 1115878 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3232. Min Act: -0.0003

Data Index: 907120 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3465. Min Act: -0.0003

Data Index: 216536 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3550. Min Act: -0.0003

Data Index: 248539 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3304. Min Act: -0.0003

Data Index: 798351 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3544. Min Act: -0.0003

Data Index: 602517 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3691. Min Act: -0.0003

Data Index: 1236130 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3405. Min Act: -0.0003

Data Index: 1181515 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3361. Min Act: -0.0003

Data Index: 595965 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3315. Min Act: -0.0003

Data Index: 875593 (C4 (Web Text))

Max Activating Token Index: 181