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

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

Neuron 4743 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.5683. Min Act: -0.0000

Data Index: 821389 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.5036. Min Act: 0.0000

Data Index: 495302 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.4985. Min Act: -0.0000

Data Index: 876838 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.4655. Min Act: -0.0000

Data Index: 881726 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.4455. Min Act: 0.0000

Data Index: 129268 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.4395. Min Act: -0.0000

Data Index: 394638 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.4269. Min Act: -0.0000

Data Index: 236614 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.4034. Min Act: -0.0000

Data Index: 258486 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1012578 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.3780. Min Act: -0.0000

Data Index: 707435 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.3856. Min Act: 0.0000

Data Index: 995371 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.3833. Min Act: -0.0000

Data Index: 603787 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.3597. Min Act: -0.0000

Data Index: 998465 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.3669. Min Act: -0.0000

Data Index: 279449 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.3792. Min Act: -0.0000

Data Index: 40630 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1358965 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1117482 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.3653. Min Act: 0.0000

Data Index: 750150 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.3788. Min Act: -0.0000

Data Index: 248749 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.5683. Min Range: -0.5683

Max Act: 0.3548. Min Act: -0.0000

Data Index: 854304 (C4 (Web Text))

Max Activating Token Index: 1012