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

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

Neuron 2189 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.4462. Min Act: -0.0000

Data Index: 261334 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.4229. Min Act: -0.0000

Data Index: 631276 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3882. Min Act: -0.0000

Data Index: 373838 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3906. Min Act: -0.0000

Data Index: 989829 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3702. Min Act: -0.0000

Data Index: 763100 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.4046. Min Act: -0.0000

Data Index: 55635 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3735. Min Act: -0.0000

Data Index: 631305 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1358642 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3591. Min Act: -0.0000

Data Index: 363208 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3658. Min Act: -0.0000

Data Index: 990675 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3458. Min Act: -0.0000

Data Index: 702203 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3852. Min Act: -0.0000

Data Index: 759821 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1167569 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3557. Min Act: -0.0000

Data Index: 741737 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3352. Min Act: -0.0000

Data Index: 502752 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3343. Min Act: -0.0000

Data Index: 886403 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3296. Min Act: -0.0000

Data Index: 262691 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3282. Min Act: -0.0000

Data Index: 747352 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1036489 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3363. Min Act: -0.0000

Data Index: 781697 (C4 (Web Text))

Max Activating Token Index: 513