Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3962 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0853. Min Act: -0.0001

Data Index: 79592 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0787. Min Act: -0.0001

Data Index: 430942 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0741. Min Act: -0.0001

Data Index: 564937 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1087947 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0692. Min Act: -0.0001

Data Index: 660801 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0714. Min Act: -0.0001

Data Index: 676652 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0708. Min Act: -0.0001

Data Index: 170129 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1415069 (Python Code)

Max Activating Token Index: 308

Text #8

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0728. Min Act: -0.0001

Data Index: 372779 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0660. Min Act: -0.0001

Data Index: 466218 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1221819 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0579. Min Act: -0.0001

Data Index: 662906 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0663. Min Act: -0.0001

Data Index: 463052 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0635. Min Act: -0.0001

Data Index: 93931 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0655. Min Act: -0.0001

Data Index: 431026 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1090348 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0624. Min Act: -0.0001

Data Index: 396481 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0598. Min Act: -0.0001

Data Index: 873559 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0624. Min Act: -0.0001

Data Index: 748957 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1347452 (C4 (Web Text))

Max Activating Token Index: 770