Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 387 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.8429. Min Act: -0.0001

Data Index: 9572 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.5136. Min Act: -0.0001

Data Index: 568805 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.6649. Min Act: -0.0001

Data Index: 883388 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.4427. Min Act: -0.0001

Data Index: 323372 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.3558. Min Act: -0.0001

Data Index: 738754 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.1113. Min Act: -0.0001

Data Index: 814512 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.3643. Min Act: -0.0001

Data Index: 1341590 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.3633. Min Act: -0.0001

Data Index: 26281 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.2786. Min Act: -0.0001

Data Index: 1176755 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.3472. Min Act: -0.0001

Data Index: 15618 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.2035. Min Act: -0.0001

Data Index: 695368 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.1727. Min Act: -0.0001

Data Index: 1282909 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.2287. Min Act: -0.0001

Data Index: 1349010 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.2257. Min Act: -0.0001

Data Index: 105326 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.2327. Min Act: -0.0001

Data Index: 327748 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.2417. Min Act: -0.0001

Data Index: 458634 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.3514. Min Act: -0.0001

Data Index: 72655 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.2636. Min Act: -0.0001

Data Index: 697570 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.1859. Min Act: -0.0001

Data Index: 938880 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 1.8429. Min Range: -1.8429

Max Act: 1.1780. Min Act: -0.0001

Data Index: 1084003 (C4 (Web Text))

Max Activating Token Index: 530