Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5052 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9808. Min Act: -0.0001

Data Index: 1432276 (Python Code)

Max Activating Token Index: 777

Text #1

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9444. Min Act: -0.0001

Data Index: 1277787 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9483. Min Act: -0.0001

Data Index: 1373800 (Python Code)

Max Activating Token Index: 271

Text #3

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1394077 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9531. Min Act: -0.0000

Data Index: 759041 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8850. Min Act: -0.0001

Data Index: 1344256 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8814. Min Act: -0.0001

Data Index: 1407333 (Python Code)

Max Activating Token Index: 93

Text #7

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8492. Min Act: -0.0000

Data Index: 758248 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8952. Min Act: -0.0001

Data Index: 1439869 (Python Code)

Max Activating Token Index: 62

Text #9

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8756. Min Act: -0.0000

Data Index: 1641669 (Python Code)

Max Activating Token Index: 970

Text #10

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8232. Min Act: -0.0001

Data Index: 1517841 (Python Code)

Max Activating Token Index: 929

Text #11

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1268537 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1276187 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7746. Min Act: -0.0001

Data Index: 1538338 (Python Code)

Max Activating Token Index: 419

Text #14

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7983. Min Act: -0.0000

Data Index: 470192 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7872. Min Act: -0.0001

Data Index: 1390737 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7766. Min Act: -0.0000

Data Index: 417325 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7849. Min Act: -0.0000

Data Index: 223521 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7838. Min Act: -0.0000

Data Index: 649167 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7496. Min Act: -0.0001

Data Index: 1530665 (Python Code)

Max Activating Token Index: 674