Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 625 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1819. Min Act: -0.0001

Data Index: 186185 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1794. Min Act: -0.0001

Data Index: 475213 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1648. Min Act: -0.0001

Data Index: 884721 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1766. Min Act: -0.0001

Data Index: 968125 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1733. Min Act: -0.0001

Data Index: 448628 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1000789 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1728. Min Act: -0.0001

Data Index: 392371 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1598. Min Act: -0.0001

Data Index: 346773 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1521. Min Act: -0.0001

Data Index: 538701 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1542. Min Act: -0.0001

Data Index: 928811 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1712. Min Act: -0.0001

Data Index: 526003 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1607. Min Act: -0.0001

Data Index: 652835 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1614. Min Act: -0.0001

Data Index: 90442 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1542. Min Act: -0.0001

Data Index: 294956 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1130432 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1527. Min Act: -0.0001

Data Index: 77980 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1696. Min Act: -0.0001

Data Index: 552080 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1648. Min Act: -0.0001

Data Index: 253848 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1552. Min Act: -0.0001

Data Index: 349808 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1524. Min Act: -0.0001

Data Index: 882876 (C4 (Web Text))

Max Activating Token Index: 112