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

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

Neuron 2435 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1731. Min Act: -0.0000

Data Index: 335803 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1672. Min Act: -0.0000

Data Index: 209307 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1682. Min Act: -0.0000

Data Index: 758220 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1645. Min Act: -0.0000

Data Index: 538701 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1747. Min Act: -0.0000

Data Index: 428795 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1619. Min Act: -0.0000

Data Index: 218152 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1522. Min Act: -0.0001

Data Index: 660240 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1555. Min Act: -0.0000

Data Index: 134034 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1485. Min Act: -0.0000

Data Index: 494178 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1605. Min Act: -0.0001

Data Index: 589582 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1557. Min Act: -0.0000

Data Index: 58109 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1320206 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1509. Min Act: -0.0001

Data Index: 315756 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1535. Min Act: -0.0000

Data Index: 678848 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1383. Min Act: -0.0000

Data Index: 233232 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1513. Min Act: -0.0000

Data Index: 790387 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1575. Min Act: -0.0000

Data Index: 887931 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1077705 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1530. Min Act: -0.0001

Data Index: 791478 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1459. Min Act: -0.0001

Data Index: 583158 (C4 (Web Text))

Max Activating Token Index: 862