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

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

Neuron 2400 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5505. Min Act: -0.0000

Data Index: 549064 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5126. Min Act: -0.0000

Data Index: 733807 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5389. Min Act: -0.0000

Data Index: 581785 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4890. Min Act: -0.0000

Data Index: 480840 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1186503 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4883. Min Act: -0.0000

Data Index: 1118995 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4897. Min Act: -0.0000

Data Index: 632546 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4897. Min Act: -0.0000

Data Index: 701535 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4729. Min Act: -0.0000

Data Index: 795423 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4979. Min Act: -0.0000

Data Index: 964083 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4468. Min Act: -0.0000

Data Index: 318873 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1263901 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4449. Min Act: -0.0000

Data Index: 940708 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4831. Min Act: -0.0000

Data Index: 245783 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4668. Min Act: -0.0000

Data Index: 178300 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1133272 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4141. Min Act: -0.0000

Data Index: 40771 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1297110 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4458. Min Act: -0.0000

Data Index: 457309 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4506. Min Act: -0.0000

Data Index: 436130 (C4 (Web Text))

Max Activating Token Index: 30