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

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

Neuron 13 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2921. Min Range: -7.2921

Max Act: 7.2921. Min Act: -0.0000

Data Index: 1056087 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 7.2921. Min Range: -7.2921

Max Act: 7.2292. Min Act: -0.0000

Data Index: 649655 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 7.2921. Min Range: -7.2921

Max Act: 6.8678. Min Act: -0.0000

Data Index: 1291638 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 7.2921. Min Range: -7.2921

Max Act: 6.6262. Min Act: -0.0000

Data Index: 1268062 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 7.2921. Min Range: -7.2921

Max Act: 6.4823. Min Act: -0.0000

Data Index: 303187 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 7.2921. Min Range: -7.2921

Max Act: 6.0770. Min Act: -0.0000

Data Index: 651542 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.6999. Min Act: -0.0000

Data Index: 1358897 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.6463. Min Act: -0.0000

Data Index: 754788 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.3496. Min Act: -0.0000

Data Index: 817459 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 7.2921. Min Range: -7.2921

Max Act: 6.5894. Min Act: -0.0000

Data Index: 941484 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.8183. Min Act: -0.0000

Data Index: 771035 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.9267. Min Act: -0.0000

Data Index: 343079 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 7.2921. Min Range: -7.2921

Max Act: 6.0792. Min Act: -0.0000

Data Index: 980487 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.6519. Min Act: -0.0000

Data Index: 298321 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.6330. Min Act: -0.0000

Data Index: 911014 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.3997. Min Act: -0.0000

Data Index: 230651 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.5950. Min Act: -0.0000

Data Index: 874216 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.3743. Min Act: -0.0000

Data Index: 445801 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.7770. Min Act: -0.0000

Data Index: 1213775 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 7.2921. Min Range: -7.2921

Max Act: 5.5706. Min Act: -0.0000

Data Index: 604821 (C4 (Web Text))

Max Activating Token Index: 904