Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1125 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0012. Min Act: -0.0005

Data Index: 1361896 (Python Code)

Max Activating Token Index: 405

Text #1

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0011. Min Act: -0.0005

Data Index: 956463 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0011. Min Act: -0.0005

Data Index: 214361 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0010. Min Act: -0.0005

Data Index: 1636070 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0010. Min Act: -0.0005

Data Index: 1596690 (Python Code)

Max Activating Token Index: 430

Text #5

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0010. Min Act: -0.0005

Data Index: 1561337 (Python Code)

Max Activating Token Index: 525

Text #6

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0010. Min Act: -0.0005

Data Index: 823937 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0010. Min Act: -0.0005

Data Index: 1634521 (Python Code)

Max Activating Token Index: 481

Text #8

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0010. Min Act: -0.0005

Data Index: 1380045 (Python Code)

Max Activating Token Index: 496

Text #9

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0009. Min Act: -0.0005

Data Index: 1503819 (Python Code)

Max Activating Token Index: 477

Text #10

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0010. Min Act: -0.0005

Data Index: 316673 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0009. Min Act: -0.0005

Data Index: 1523230 (Python Code)

Max Activating Token Index: 458

Text #12

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0009. Min Act: -0.0005

Data Index: 207599 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0009. Min Act: -0.0005

Data Index: 1527596 (Python Code)

Max Activating Token Index: 516

Text #14

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0009. Min Act: -0.0005

Data Index: 675211 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0009. Min Act: -0.0005

Data Index: 1558511 (Python Code)

Max Activating Token Index: 381

Text #16

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0009. Min Act: -0.0005

Data Index: 1504120 (Python Code)

Max Activating Token Index: 410

Text #17

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0009. Min Act: -0.0005

Data Index: 1551551 (Python Code)

Max Activating Token Index: 328

Text #18

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0009. Min Act: -0.0005

Data Index: 1613015 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0009. Min Act: -0.0005

Data Index: 218123 (C4 (Web Text))

Max Activating Token Index: 474