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

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

Neuron 4275 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: 0.1914. Min Range: -0.1914

Max Act: 0.1914. Min Act: -0.0002

Data Index: 529065 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1829. Min Act: -0.0002

Data Index: 913089 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1792. Min Act: -0.0002

Data Index: 640098 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1826. Min Act: -0.0002

Data Index: 95271 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1795. Min Act: -0.0002

Data Index: 1252608 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1750. Min Act: -0.0002

Data Index: 472456 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1738. Min Act: -0.0002

Data Index: 1032203 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1734. Min Act: -0.0002

Data Index: 1136194 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1666. Min Act: -0.0002

Data Index: 1197368 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1670. Min Act: -0.0002

Data Index: 13088 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1648. Min Act: -0.0002

Data Index: 394168 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1594. Min Act: -0.0002

Data Index: 491938 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1599. Min Act: -0.0002

Data Index: 550970 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1588. Min Act: -0.0002

Data Index: 22028 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1571. Min Act: -0.0002

Data Index: 388274 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1581. Min Act: -0.0002

Data Index: 934316 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1566. Min Act: -0.0002

Data Index: 1323531 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1527. Min Act: -0.0002

Data Index: 17858 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1533. Min Act: -0.0002

Data Index: 882498 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1542. Min Act: -0.0002

Data Index: 1105032 (C4 (Web Text))

Max Activating Token Index: 338