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

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

Neuron 5 in Layer 0

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: 0.2032. Min Range: -0.2032

Max Act: 0.2032. Min Act: -0.0001

Data Index: 347883 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.2005. Min Act: -0.0001

Data Index: 337208 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1992. Min Act: -0.0001

Data Index: 1301456 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1309537 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1763. Min Act: -0.0001

Data Index: 985741 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1737. Min Act: -0.0001

Data Index: 87582 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1765. Min Act: -0.0001

Data Index: 1096391 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1717. Min Act: -0.0001

Data Index: 536170 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1746. Min Act: -0.0001

Data Index: 674797 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1767. Min Act: -0.0001

Data Index: 306892 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1715. Min Act: -0.0001

Data Index: 992593 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1737. Min Act: -0.0001

Data Index: 346952 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1749. Min Act: -0.0001

Data Index: 235748 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1764. Min Act: -0.0001

Data Index: 665821 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1712. Min Act: -0.0001

Data Index: 271948 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1692. Min Act: -0.0001

Data Index: 258604 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1732. Min Act: -0.0001

Data Index: 1171718 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1704. Min Act: -0.0001

Data Index: 561507 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1654. Min Act: -0.0001

Data Index: 501214 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1652. Min Act: -0.0001

Data Index: 21176 (C4 (Web Text))

Max Activating Token Index: 116