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

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

Neuron 1051 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.7987. Min Act: -0.0000

Data Index: 54157 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 4.0081. Min Range: -4.0081

Max Act: 4.0081. Min Act: -0.0000

Data Index: 747555 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.6619. Min Act: -0.0000

Data Index: 1031571 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.8201. Min Act: -0.0000

Data Index: 291647 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.6703. Min Act: -0.0000

Data Index: 639307 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.5373. Min Act: -0.0000

Data Index: 464754 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.5396. Min Act: -0.0000

Data Index: 1268712 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.4795. Min Act: -0.0000

Data Index: 1098704 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.3551. Min Act: -0.0000

Data Index: 598645 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.3598. Min Act: -0.0000

Data Index: 982652 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.3429. Min Act: -0.0000

Data Index: 98611 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.3958. Min Act: -0.0000

Data Index: 865013 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.2170. Min Act: -0.0000

Data Index: 1013020 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.2173. Min Act: -0.0000

Data Index: 84585 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.2079. Min Act: -0.0000

Data Index: 580291 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.1077. Min Act: -0.0000

Data Index: 940566 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.3906. Min Act: -0.0000

Data Index: 15453 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.0886. Min Act: -0.0000

Data Index: 197695 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.3673. Min Act: -0.0000

Data Index: 1240108 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.0629. Min Act: -0.0000

Data Index: 580885 (C4 (Web Text))

Max Activating Token Index: 675