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

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

Neuron 1021 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.6538. Min Act: -0.0000

Data Index: 170861 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1375407 (Python Code)

Max Activating Token Index: 74

Text #2

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1424557 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.0786. Min Act: -0.0000

Data Index: 359711 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.9734. Min Act: -0.0000

Data Index: 102871 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.9571. Min Act: -0.0000

Data Index: 365717 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1460082 (Python Code)

Max Activating Token Index: 763

Text #7

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.0018. Min Act: -0.0000

Data Index: 286404 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.8819. Min Act: -0.0000

Data Index: 338300 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.9709. Min Act: -0.0000

Data Index: 396278 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1650163 (Python Code)

Max Activating Token Index: 904

Text #11

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.8716. Min Act: -0.0000

Data Index: 998476 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1453574 (Python Code)

Max Activating Token Index: 845

Text #13

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1013216 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1479064 (Python Code)

Max Activating Token Index: 236

Text #15

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.8583. Min Act: 0.0000

Data Index: 1578320 (Python Code)

Max Activating Token Index: 102

Text #16

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.9422. Min Act: -0.0000

Data Index: 919221 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.8658. Min Act: -0.0000

Data Index: 918351 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.7959. Min Act: -0.0000

Data Index: 460391 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 1.6538. Min Range: -1.6538

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1590164 (Python Code)

Max Activating Token Index: 463