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

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

Neuron 1514 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: 0.9822. Min Range: -0.9822

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1073427 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.6856. Min Act: -0.0000

Data Index: 580551 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1233593 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1586664 (Python Code)

Max Activating Token Index: 715

Text #4

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.6337. Min Act: -0.0000

Data Index: 998194 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.6067. Min Act: -0.0000

Data Index: 519506 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1333831 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1050800 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5570. Min Act: -0.0000

Data Index: 900962 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5948. Min Act: -0.0000

Data Index: 336457 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.6230. Min Act: -0.0000

Data Index: 540661 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5680. Min Act: -0.0000

Data Index: 92229 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5815. Min Act: -0.0000

Data Index: 423479 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5999. Min Act: -0.0000

Data Index: 506592 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1167756 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1580422 (Python Code)

Max Activating Token Index: 756

Text #16

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5648. Min Act: -0.0000

Data Index: 160021 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5537. Min Act: -0.0000

Data Index: 81942 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1285002 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1470707 (Python Code)

Max Activating Token Index: 802