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

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

Neuron 5766 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: 0.1909. Min Range: -0.1909

Max Act: 0.1875. Min Act: -0.0001

Data Index: 405380 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1909. Min Act: -0.0001

Data Index: 726996 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1868. Min Act: -0.0001

Data Index: 862894 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1835. Min Act: -0.0001

Data Index: 205671 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1785. Min Act: -0.0001

Data Index: 409273 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1140769 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1730. Min Act: -0.0001

Data Index: 445182 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1760. Min Act: -0.0001

Data Index: 1245376 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1710. Min Act: -0.0001

Data Index: 296725 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1757. Min Act: -0.0001

Data Index: 654617 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1710. Min Act: -0.0001

Data Index: 357309 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1088967 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1703. Min Act: -0.0001

Data Index: 195504 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1710. Min Act: -0.0001

Data Index: 959782 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1665. Min Act: -0.0001

Data Index: 936416 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1659. Min Act: -0.0001

Data Index: 458457 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1047766 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1654. Min Act: -0.0001

Data Index: 1325050 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1233215 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1671. Min Act: -0.0001

Data Index: 1333915 (C4 (Web Text))

Max Activating Token Index: 24