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

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

Neuron 4922 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: 1.0040. Min Range: -1.0040

Max Act: 0.9565. Min Act: -0.0000

Data Index: 310804 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 1.0040. Min Range: -1.0040

Max Act: 1.0040. Min Act: -0.0000

Data Index: 333458 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.9403. Min Act: -0.0000

Data Index: 358826 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1228146 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.9243. Min Act: -0.0000

Data Index: 610800 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.9495. Min Act: -0.0000

Data Index: 916823 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.9149. Min Act: -0.0000

Data Index: 140587 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8569. Min Act: -0.0000

Data Index: 816812 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8426. Min Act: -0.0000

Data Index: 433578 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8288. Min Act: -0.0000

Data Index: 239674 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1112071 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8859. Min Act: -0.0000

Data Index: 1098401 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8651. Min Act: -0.0000

Data Index: 989724 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8604. Min Act: -0.0000

Data Index: 180818 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1121389 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8651. Min Act: -0.0000

Data Index: 399804 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8149. Min Act: -0.0000

Data Index: 597722 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1334599 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8548. Min Act: -0.0000

Data Index: 431113 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.0040. Min Range: -1.0040

Max Act: 0.8663. Min Act: -0.0000

Data Index: 988457 (C4 (Web Text))

Max Activating Token Index: 503