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

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

Neuron 2314 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: 0.2001. Min Range: -0.2001

Max Act: 0.2001. Min Act: -0.0002

Data Index: 943854 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1930. Min Act: -0.0002

Data Index: 416354 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1952. Min Act: -0.0002

Data Index: 902551 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1922. Min Act: -0.0002

Data Index: 1074092 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1831. Min Act: -0.0002

Data Index: 691417 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1795. Min Act: -0.0002

Data Index: 501594 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1836. Min Act: -0.0002

Data Index: 377835 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1776. Min Act: -0.0002

Data Index: 1054047 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1755. Min Act: -0.0002

Data Index: 1109995 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1755. Min Act: -0.0002

Data Index: 51600 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1696. Min Act: -0.0002

Data Index: 692245 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1699. Min Act: -0.0002

Data Index: 1126708 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1691. Min Act: -0.0002

Data Index: 937890 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1686. Min Act: -0.0002

Data Index: 1142000 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1672. Min Act: -0.0002

Data Index: 565427 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1644. Min Act: -0.0002

Data Index: 1228155 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1619. Min Act: -0.0002

Data Index: 808225 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1615. Min Act: -0.0003

Data Index: 842670 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1634. Min Act: -0.0002

Data Index: 3865 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1652. Min Act: -0.0002

Data Index: 1054087 (C4 (Web Text))

Max Activating Token Index: 76