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

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

Neuron 1502 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: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0004

Data Index: 7393 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0650. Min Act: -0.0003

Data Index: 343148 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0636. Min Act: -0.0003

Data Index: 249099 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0641. Min Act: -0.0003

Data Index: 112708 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0641. Min Act: -0.0004

Data Index: 813429 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1252148 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0637. Min Act: -0.0003

Data Index: 814052 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0612. Min Act: -0.0003

Data Index: 249694 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0608. Min Act: -0.0003

Data Index: 956251 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0588. Min Act: -0.0003

Data Index: 73117 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0589. Min Act: -0.0003

Data Index: 116692 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0620. Min Act: -0.0003

Data Index: 21081 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0582. Min Act: -0.0003

Data Index: 562240 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0602. Min Act: -0.0004

Data Index: 849358 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1182837 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0590. Min Act: -0.0003

Data Index: 1161035 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0585. Min Act: -0.0003

Data Index: 174102 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0593. Min Act: -0.0003

Data Index: 377322 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0580. Min Act: -0.0003

Data Index: 1107774 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0580. Min Act: -0.0003

Data Index: 1020274 (C4 (Web Text))

Max Activating Token Index: 733