Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4087 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1945. Min Act: -0.0001

Data Index: 989720 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1769. Min Act: -0.0001

Data Index: 1530355 (Python Code)

Max Activating Token Index: 685

Text #2

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1761. Min Act: -0.0001

Data Index: 106584 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1454420 (Python Code)

Max Activating Token Index: 619

Text #4

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1800. Min Act: -0.0001

Data Index: 1388547 (Python Code)

Max Activating Token Index: 557

Text #5

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1476032 (Python Code)

Max Activating Token Index: 556

Text #6

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1726. Min Act: -0.0001

Data Index: 1500536 (Python Code)

Max Activating Token Index: 204

Text #7

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1594132 (Python Code)

Max Activating Token Index: 324

Text #8

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1621. Min Act: -0.0001

Data Index: 1561387 (Python Code)

Max Activating Token Index: 126

Text #9

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1697. Min Act: -0.0001

Data Index: 1453315 (Python Code)

Max Activating Token Index: 813

Text #10

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1485973 (Python Code)

Max Activating Token Index: 461

Text #11

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1545437 (Python Code)

Max Activating Token Index: 358

Text #12

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1582. Min Act: -0.0001

Data Index: 1619076 (Python Code)

Max Activating Token Index: 621

Text #13

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1491234 (Python Code)

Max Activating Token Index: 741

Text #14

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1397481 (Python Code)

Max Activating Token Index: 894

Text #15

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1505502 (Python Code)

Max Activating Token Index: 398

Text #16

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1467063 (Python Code)

Max Activating Token Index: 671

Text #17

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1337. Min Act: -0.0001

Data Index: 1372843 (Python Code)

Max Activating Token Index: 232

Text #18

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1405442 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1529404 (Python Code)

Max Activating Token Index: 2