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

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

Neuron 2559 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1794. Min Act: -0.0001

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1666. Min Act: -0.0001

Data Index: 928899 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1631. Min Act: -0.0001

Data Index: 796421 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1545. Min Act: -0.0001

Data Index: 104844 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1315512 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1537. Min Act: -0.0001

Data Index: 24416 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1516. Min Act: -0.0001

Data Index: 714623 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1297835 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1497. Min Act: -0.0001

Data Index: 1287514 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1478. Min Act: -0.0001

Data Index: 1248859 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1441. Min Act: -0.0001

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1442. Min Act: -0.0001

Data Index: 167998 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1068760 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1389. Min Act: -0.0001

Data Index: 797477 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1420. Min Act: -0.0001

Data Index: 230797 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1420. Min Act: -0.0001

Data Index: 107951 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1235445 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1403. Min Act: -0.0001

Data Index: 377515 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1043100 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1259975 (C4 (Web Text))

Max Activating Token Index: 631