Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 41 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0003

Data Index: 176912 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0638. Min Act: -0.0003

Data Index: 415052 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1198905 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0627. Min Act: -0.0003

Data Index: 145800 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0634. Min Act: -0.0003

Data Index: 354386 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1292529 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0606. Min Act: -0.0003

Data Index: 19118 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0603. Min Act: -0.0003

Data Index: 47028 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0611. Min Act: -0.0003

Data Index: 184150 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0646. Min Act: -0.0003

Data Index: 242638 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0607. Min Act: -0.0003

Data Index: 806458 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0572. Min Act: -0.0003

Data Index: 663579 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0558. Min Act: -0.0003

Data Index: 82772 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1334240 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1150584 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1267854 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1099262 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0582. Min Act: -0.0003

Data Index: 212363 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1140724 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1067359 (C4 (Web Text))

Max Activating Token Index: 564