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

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

Neuron 3474 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: 0.1700. Min Range: -0.1700

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1314058 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1677. Min Act: -0.0000

Data Index: 502291 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1290534 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1525399 (Python Code)

Max Activating Token Index: 335

Text #4

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1607. Min Act: -0.0000

Data Index: 893720 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1572. Min Act: -0.0000

Data Index: 231752 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1586. Min Act: -0.0000

Data Index: 520131 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1489. Min Act: 0.0000

Data Index: 1072845 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1471799 (Python Code)

Max Activating Token Index: 521

Text #9

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1561. Min Act: -0.0001

Data Index: 897604 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1453. Min Act: -0.0001

Data Index: 128491 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1300808 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1329499 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1475. Min Act: -0.0001

Data Index: 12321 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1483. Min Act: -0.0000

Data Index: 284794 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1342949 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1488056 (Python Code)

Max Activating Token Index: 575

Text #17

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1456. Min Act: -0.0001

Data Index: 821703 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1096110 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1027327 (C4 (Web Text))

Max Activating Token Index: 730