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

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

Neuron 4364 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2825. Min Act: -0.0000

Data Index: 454052 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1579146 (Python Code)

Max Activating Token Index: 368

Text #2

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1546828 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1458586 (Python Code)

Max Activating Token Index: 834

Text #4

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1878. Min Act: -0.0000

Data Index: 913431 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1550166 (Python Code)

Max Activating Token Index: 794

Text #6

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1432839 (Python Code)

Max Activating Token Index: 565

Text #7

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1752. Min Act: -0.0000

Data Index: 957152 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1100035 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1639. Min Act: -0.0000

Data Index: 733626 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1645584 (Python Code)

Max Activating Token Index: 1015

Text #11

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1435. Min Act: -0.0000

Data Index: 657728 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1541. Min Act: -0.0000

Data Index: 420608 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1510. Min Act: -0.0000

Data Index: 654945 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1523. Min Act: -0.0000

Data Index: 700587 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1553. Min Act: -0.0000

Data Index: 624494 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1465808 (Python Code)

Max Activating Token Index: 152

Text #17

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1284348 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1628719 (Python Code)

Max Activating Token Index: 741

Text #19

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1578845 (Python Code)

Max Activating Token Index: 720