Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3974 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2236. Min Act: -0.0003

Data Index: 1366462 (Python Code)

Max Activating Token Index: 186

Text #1

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2130. Min Act: -0.0003

Data Index: 1431146 (Python Code)

Max Activating Token Index: 228

Text #2

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1979. Min Act: -0.0003

Data Index: 1361797 (Python Code)

Max Activating Token Index: 633

Text #3

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1925. Min Act: -0.0003

Data Index: 1453819 (Python Code)

Max Activating Token Index: 449

Text #4

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1918. Min Act: -0.0003

Data Index: 1377937 (Python Code)

Max Activating Token Index: 19

Text #5

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1890. Min Act: -0.0003

Data Index: 1448355 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1856. Min Act: -0.0003

Data Index: 1508037 (Python Code)

Max Activating Token Index: 61

Text #7

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1779. Min Act: -0.0003

Data Index: 1445128 (Python Code)

Max Activating Token Index: 201

Text #8

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1695. Min Act: -0.0003

Data Index: 1515101 (Python Code)

Max Activating Token Index: 516

Text #9

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1734. Min Act: -0.0003

Data Index: 1424856 (Python Code)

Max Activating Token Index: 192

Text #10

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1727. Min Act: -0.0003

Data Index: 1409423 (Python Code)

Max Activating Token Index: 207

Text #11

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1647. Min Act: -0.0003

Data Index: 1402039 (Python Code)

Max Activating Token Index: 207

Text #12

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1699. Min Act: -0.0003

Data Index: 1363904 (Python Code)

Max Activating Token Index: 706

Text #13

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1678. Min Act: -0.0003

Data Index: 1432343 (Python Code)

Max Activating Token Index: 467

Text #14

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1583. Min Act: -0.0003

Data Index: 1403270 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1697. Min Act: -0.0003

Data Index: 1624383 (Python Code)

Max Activating Token Index: 386

Text #16

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1628. Min Act: -0.0003

Data Index: 1532548 (Python Code)

Max Activating Token Index: 462

Text #17

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1611. Min Act: -0.0003

Data Index: 1637484 (Python Code)

Max Activating Token Index: 133

Text #18

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1546. Min Act: -0.0003

Data Index: 1372749 (Python Code)

Max Activating Token Index: 102

Text #19

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1545. Min Act: -0.0003

Data Index: 1560134 (Python Code)

Max Activating Token Index: 699