Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1557 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9459. Min Range: -2.9459

Max Act: 2.9459. Min Act: -0.0000

Data Index: 1604290 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 2.9459. Min Range: -2.9459

Max Act: 2.3008. Min Act: -0.0000

Data Index: 1473481 (Python Code)

Max Activating Token Index: 327

Text #2

Max Range: 2.9459. Min Range: -2.9459

Max Act: 2.2350. Min Act: -0.0000

Data Index: 1560817 (Python Code)

Max Activating Token Index: 1003

Text #3

Max Range: 2.9459. Min Range: -2.9459

Max Act: 2.0854. Min Act: -0.0000

Data Index: 1529729 (Python Code)

Max Activating Token Index: 735

Text #4

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.8748. Min Act: -0.0000

Data Index: 1518443 (Python Code)

Max Activating Token Index: 457

Text #5

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.8718. Min Act: -0.0000

Data Index: 1026691 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.7524. Min Act: -0.0000

Data Index: 390793 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.8448. Min Act: -0.0000

Data Index: 1407100 (Python Code)

Max Activating Token Index: 514

Text #8

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.7479. Min Act: -0.0000

Data Index: 1555729 (Python Code)

Max Activating Token Index: 848

Text #9

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.8548. Min Act: -0.0000

Data Index: 1365227 (Python Code)

Max Activating Token Index: 157

Text #10

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.8558. Min Act: -0.0000

Data Index: 1343803 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.8420. Min Act: -0.0000

Data Index: 953100 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.8425. Min Act: -0.0000

Data Index: 417775 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.8341. Min Act: -0.0000

Data Index: 1567847 (Python Code)

Max Activating Token Index: 645

Text #14

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.7138. Min Act: -0.0000

Data Index: 1443432 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.7030. Min Act: -0.0000

Data Index: 1581461 (Python Code)

Max Activating Token Index: 697

Text #16

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.5970. Min Act: -0.0000

Data Index: 1542201 (Python Code)

Max Activating Token Index: 1004

Text #17

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.6828. Min Act: -0.0000

Data Index: 1522333 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.6742. Min Act: -0.0000

Data Index: 1365150 (Python Code)

Max Activating Token Index: 605

Text #19

Max Range: 2.9459. Min Range: -2.9459

Max Act: 1.7836. Min Act: -0.0000

Data Index: 747842 (C4 (Web Text))

Max Activating Token Index: 729