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

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

Neuron 3042 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1902. Min Act: -0.0002

Data Index: 1485085 (Python Code)

Max Activating Token Index: 119

Text #1

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1653. Min Act: -0.0002

Data Index: 1629372 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1632. Min Act: -0.0002

Data Index: 1475549 (Python Code)

Max Activating Token Index: 754

Text #3

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1599. Min Act: -0.0002

Data Index: 1419264 (Python Code)

Max Activating Token Index: 696

Text #4

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1628. Min Act: -0.0002

Data Index: 1419939 (Python Code)

Max Activating Token Index: 825

Text #5

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1630. Min Act: -0.0002

Data Index: 1624832 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1607. Min Act: -0.0002

Data Index: 1457627 (Python Code)

Max Activating Token Index: 163

Text #7

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1632. Min Act: -0.0002

Data Index: 1613439 (Python Code)

Max Activating Token Index: 580

Text #8

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1625. Min Act: -0.0002

Data Index: 1625482 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1582. Min Act: -0.0002

Data Index: 1591886 (Python Code)

Max Activating Token Index: 760

Text #10

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1549. Min Act: -0.0002

Data Index: 1414111 (Python Code)

Max Activating Token Index: 285

Text #11

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1594. Min Act: -0.0002

Data Index: 1409320 (Python Code)

Max Activating Token Index: 90

Text #12

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1540. Min Act: -0.0002

Data Index: 1398694 (Python Code)

Max Activating Token Index: 999

Text #13

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1529. Min Act: -0.0002

Data Index: 1482645 (Python Code)

Max Activating Token Index: 717

Text #14

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1547. Min Act: -0.0002

Data Index: 1602378 (Python Code)

Max Activating Token Index: 964

Text #15

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1553. Min Act: -0.0002

Data Index: 1401215 (Python Code)

Max Activating Token Index: 731

Text #16

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1531. Min Act: -0.0002

Data Index: 1396340 (Python Code)

Max Activating Token Index: 626

Text #17

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1528. Min Act: -0.0002

Data Index: 1571607 (Python Code)

Max Activating Token Index: 287

Text #18

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1493. Min Act: -0.0002

Data Index: 1400979 (Python Code)

Max Activating Token Index: 740

Text #19

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1498. Min Act: -0.0002

Data Index: 1435840 (Python Code)

Max Activating Token Index: 305