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

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

Neuron 4402 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.9870. Min Act: 0.0008

Data Index: 410883 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.6974. Min Act: -0.0000

Data Index: 342547 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.5540. Min Act: -0.0000

Data Index: 601932 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.4021. Min Act: -0.0000

Data Index: 640094 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.4160. Min Act: -0.0000

Data Index: 248988 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.3730. Min Act: 0.0001

Data Index: 882308 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.1658. Min Act: -0.0000

Data Index: 365788 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.1597. Min Act: -0.0000

Data Index: 622206 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.5183. Min Act: 0.0008

Data Index: 205019 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.1113. Min Act: -0.0000

Data Index: 325094 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.4868. Min Act: -0.0000

Data Index: 709217 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.2907. Min Act: -0.0000

Data Index: 151071 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 7.9870. Min Range: -7.9870

Max Act: 6.9339. Min Act: -0.0000

Data Index: 1017061 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 7.9870. Min Range: -7.9870

Max Act: 6.9898. Min Act: -0.0000

Data Index: 705536 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.1858. Min Act: -0.0000

Data Index: 1047649 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.1412. Min Act: -0.0000

Data Index: 707190 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.1066. Min Act: -0.0000

Data Index: 124658 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 7.9870. Min Range: -7.9870

Max Act: 7.0925. Min Act: 0.0008

Data Index: 670296 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 7.9870. Min Range: -7.9870

Max Act: 6.9791. Min Act: -0.0000

Data Index: 245424 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 7.9870. Min Range: -7.9870

Max Act: 6.9572. Min Act: -0.0000

Data Index: 626393 (C4 (Web Text))

Max Activating Token Index: 112