Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1928 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0003

Data Index: 125653 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0814. Min Act: -0.0003

Data Index: 1353998 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0690. Min Act: -0.0003

Data Index: 511326 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0688. Min Act: -0.0003

Data Index: 1164356 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0679. Min Act: -0.0003

Data Index: 805630 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0657. Min Act: -0.0003

Data Index: 283229 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0646. Min Act: -0.0003

Data Index: 960615 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0641. Min Act: -0.0004

Data Index: 622124 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1307363 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0618. Min Act: -0.0003

Data Index: 1056381 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1305320 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0610. Min Act: -0.0003

Data Index: 707052 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0586. Min Act: -0.0004

Data Index: 372513 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0582. Min Act: -0.0004

Data Index: 279541 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1004410 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0583. Min Act: -0.0004

Data Index: 547124 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0573. Min Act: -0.0004

Data Index: 854112 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0583. Min Act: -0.0003

Data Index: 180780 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1157905 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0558. Min Act: -0.0004

Data Index: 1097703 (C4 (Web Text))

Max Activating Token Index: 136