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

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

Neuron 114 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1467. Min Range: -1.1467

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1573589 (Python Code)

Max Activating Token Index: 94

Text #1

Max Range: 1.1467. Min Range: -1.1467

Max Act: 1.1453. Min Act: -0.0000

Data Index: 1556292 (Python Code)

Max Activating Token Index: 315

Text #2

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1388715 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.8922. Min Act: -0.0000

Data Index: 915506 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1597704 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.8106. Min Act: 0.0000

Data Index: 840097 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1548559 (Python Code)

Max Activating Token Index: 657

Text #7

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.8057. Min Act: 0.0001

Data Index: 1574994 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1532194 (Python Code)

Max Activating Token Index: 729

Text #9

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.7848. Min Act: 0.0001

Data Index: 1397430 (Python Code)

Max Activating Token Index: 516

Text #10

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1558777 (Python Code)

Max Activating Token Index: 803

Text #11

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1631537 (Python Code)

Max Activating Token Index: 560

Text #12

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.7272. Min Act: -0.0000

Data Index: 672602 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.7219. Min Act: 0.0000

Data Index: 1303020 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1388693 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1445870 (Python Code)

Max Activating Token Index: 755

Text #16

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.7157. Min Act: 0.0000

Data Index: 1041381 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.6873. Min Act: -0.0000

Data Index: 124374 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.6870. Min Act: -0.0000

Data Index: 246581 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 1.1467. Min Range: -1.1467

Max Act: 0.7276. Min Act: 0.0001

Data Index: 1588035 (Python Code)

Max Activating Token Index: 54