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

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

Neuron 1721 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1818. Min Act: -0.0000

Data Index: 942901 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1396056 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1379431 (Python Code)

Max Activating Token Index: 867

Text #3

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1575102 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1673. Min Act: -0.0000

Data Index: 195890 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1634359 (Python Code)

Max Activating Token Index: 804

Text #6

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1666. Min Act: -0.0000

Data Index: 158563 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1549. Min Act: -0.0001

Data Index: 453118 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1651. Min Act: -0.0000

Data Index: 846445 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1523. Min Act: -0.0000

Data Index: 215070 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1611788 (Python Code)

Max Activating Token Index: 933

Text #11

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1551. Min Act: -0.0001

Data Index: 317162 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1530. Min Act: -0.0001

Data Index: 390851 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1442535 (Python Code)

Max Activating Token Index: 540

Text #14

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1468. Min Act: -0.0001

Data Index: 110599 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1512. Min Act: -0.0000

Data Index: 926844 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1510127 (Python Code)

Max Activating Token Index: 708

Text #17

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1499. Min Act: -0.0000

Data Index: 439031 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1525464 (Python Code)

Max Activating Token Index: 435

Text #19

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1451461 (Python Code)

Max Activating Token Index: 292