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

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

Neuron 5600 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1420. Min Range: -4.1420

Max Act: 4.1420. Min Act: -0.0000

Data Index: 967848 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 4.1420. Min Range: -4.1420

Max Act: 4.1014. Min Act: -0.0000

Data Index: 491729 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 4.1420. Min Range: -4.1420

Max Act: 3.9462. Min Act: -0.0000

Data Index: 103817 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 4.1420. Min Range: -4.1420

Max Act: 3.3253. Min Act: -0.0000

Data Index: 1548284 (Python Code)

Max Activating Token Index: 854

Text #4

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.9535. Min Act: -0.0000

Data Index: 773216 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.9234. Min Act: -0.0000

Data Index: 1001874 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 4.1420. Min Range: -4.1420

Max Act: 3.1100. Min Act: -0.0000

Data Index: 359068 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 4.1420. Min Range: -4.1420

Max Act: 3.1684. Min Act: -0.0000

Data Index: 1516563 (Python Code)

Max Activating Token Index: 792

Text #8

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.6828. Min Act: -0.0000

Data Index: 120781 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 4.1420. Min Range: -4.1420

Max Act: 3.1651. Min Act: -0.0000

Data Index: 1412801 (Python Code)

Max Activating Token Index: 658

Text #10

Max Range: 4.1420. Min Range: -4.1420

Max Act: 3.1693. Min Act: -0.0000

Data Index: 1424812 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.8281. Min Act: -0.0000

Data Index: 1340504 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.5650. Min Act: -0.0000

Data Index: 1252365 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.8063. Min Act: -0.0000

Data Index: 1516125 (Python Code)

Max Activating Token Index: 876

Text #14

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.6541. Min Act: -0.0000

Data Index: 117877 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.7408. Min Act: -0.0000

Data Index: 1454109 (Python Code)

Max Activating Token Index: 490

Text #16

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.8590. Min Act: -0.0000

Data Index: 1561496 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.7004. Min Act: -0.0000

Data Index: 1581284 (Python Code)

Max Activating Token Index: 709

Text #18

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.1546. Min Act: -0.0000

Data Index: 1109586 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 4.1420. Min Range: -4.1420

Max Act: 2.7250. Min Act: -0.0000

Data Index: 1550382 (Python Code)

Max Activating Token Index: 950