Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4912 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1784. Min Act: -0.0001

Data Index: 118658 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1771. Min Act: -0.0001

Data Index: 446769 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1682. Min Act: -0.0001

Data Index: 483268 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1727. Min Act: -0.0001

Data Index: 1017553 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1603. Min Act: -0.0001

Data Index: 583194 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1650. Min Act: -0.0001

Data Index: 97775 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1698. Min Act: -0.0001

Data Index: 880980 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1514. Min Act: -0.0001

Data Index: 1150144 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1482. Min Act: -0.0001

Data Index: 734990 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1659. Min Act: -0.0001

Data Index: 1319273 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1504. Min Act: -0.0001

Data Index: 768942 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1688. Min Act: -0.0001

Data Index: 614653 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1590. Min Act: -0.0001

Data Index: 837363 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1528. Min Act: -0.0001

Data Index: 163065 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1461. Min Act: -0.0001

Data Index: 469935 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1540. Min Act: -0.0001

Data Index: 67998 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1554. Min Act: -0.0001

Data Index: 396259 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1489. Min Act: -0.0001

Data Index: 445319 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1583. Min Act: -0.0001

Data Index: 356488 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1579. Min Act: -0.0001

Data Index: 834203 (C4 (Web Text))

Max Activating Token Index: 14