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

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

Neuron 1960 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: 5.4629. Min Range: -5.4629

Max Act: 5.4629. Min Act: -0.0000

Data Index: 1570708 (Python Code)

Max Activating Token Index: 238

Text #1

Max Range: 5.4629. Min Range: -5.4629

Max Act: 5.1127. Min Act: 0.0000

Data Index: 1499662 (Python Code)

Max Activating Token Index: 608

Text #2

Max Range: 5.4629. Min Range: -5.4629

Max Act: 4.4265. Min Act: -0.0000

Data Index: 1448212 (Python Code)

Max Activating Token Index: 714

Text #3

Max Range: 5.4629. Min Range: -5.4629

Max Act: 4.0903. Min Act: -0.0000

Data Index: 1516571 (Python Code)

Max Activating Token Index: 697

Text #4

Max Range: 5.4629. Min Range: -5.4629

Max Act: 4.1036. Min Act: -0.0000

Data Index: 1458915 (Python Code)

Max Activating Token Index: 296

Text #5

Max Range: 5.4629. Min Range: -5.4629

Max Act: 4.2312. Min Act: -0.0000

Data Index: 1373684 (Python Code)

Max Activating Token Index: 613

Text #6

Max Range: 5.4629. Min Range: -5.4629

Max Act: 4.1306. Min Act: -0.0000

Data Index: 1638732 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 5.4629. Min Range: -5.4629

Max Act: 4.2864. Min Act: -0.0000

Data Index: 1375167 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 5.4629. Min Range: -5.4629

Max Act: 3.9819. Min Act: -0.0000

Data Index: 1582411 (Python Code)

Max Activating Token Index: 103

Text #9

Max Range: 5.4629. Min Range: -5.4629

Max Act: 4.1214. Min Act: -0.0000

Data Index: 1457720 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 5.4629. Min Range: -5.4629

Max Act: 3.9190. Min Act: -0.0000

Data Index: 1633883 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 5.4629. Min Range: -5.4629

Max Act: 3.7327. Min Act: 0.0000

Data Index: 1279886 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 5.4629. Min Range: -5.4629

Max Act: 3.9639. Min Act: 0.0000

Data Index: 978295 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 5.4629. Min Range: -5.4629

Max Act: 3.9635. Min Act: -0.0000

Data Index: 1612756 (Python Code)

Max Activating Token Index: 350

Text #14

Max Range: 5.4629. Min Range: -5.4629

Max Act: 3.4642. Min Act: -0.0000

Data Index: 1370271 (Python Code)

Max Activating Token Index: 780

Text #15

Max Range: 5.4629. Min Range: -5.4629

Max Act: 3.6500. Min Act: -0.0000

Data Index: 1471346 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 5.4629. Min Range: -5.4629

Max Act: 3.7851. Min Act: -0.0000

Data Index: 1578864 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 5.4629. Min Range: -5.4629

Max Act: 3.8222. Min Act: -0.0000

Data Index: 1492565 (Python Code)

Max Activating Token Index: 360

Text #18

Max Range: 5.4629. Min Range: -5.4629

Max Act: 3.5150. Min Act: -0.0000

Data Index: 1546070 (Python Code)

Max Activating Token Index: 778

Text #19

Max Range: 5.4629. Min Range: -5.4629

Max Act: 3.6271. Min Act: -0.0000

Data Index: 1519037 (Python Code)

Max Activating Token Index: 596