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

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

Neuron 1144 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7236. Min Range: -5.7236

Max Act: 5.6272. Min Act: -0.0000

Data Index: 1242582 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 5.7236. Min Range: -5.7236

Max Act: 5.7236. Min Act: -0.0000

Data Index: 393312 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 5.7236. Min Range: -5.7236

Max Act: 5.3150. Min Act: -0.0000

Data Index: 1594282 (Python Code)

Max Activating Token Index: 344

Text #3

Max Range: 5.7236. Min Range: -5.7236

Max Act: 5.2567. Min Act: -0.0000

Data Index: 1466137 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 5.7236. Min Range: -5.7236

Max Act: 5.0557. Min Act: -0.0000

Data Index: 1449966 (Python Code)

Max Activating Token Index: 682

Text #5

Max Range: 5.7236. Min Range: -5.7236

Max Act: 4.4515. Min Act: -0.0000

Data Index: 1392029 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 5.7236. Min Range: -5.7236

Max Act: 4.3415. Min Act: -0.0000

Data Index: 1576739 (Python Code)

Max Activating Token Index: 125

Text #7

Max Range: 5.7236. Min Range: -5.7236

Max Act: 4.3266. Min Act: -0.0000

Data Index: 1465451 (Python Code)

Max Activating Token Index: 948

Text #8

Max Range: 5.7236. Min Range: -5.7236

Max Act: 4.2244. Min Act: -0.0000

Data Index: 1377527 (Python Code)

Max Activating Token Index: 951

Text #9

Max Range: 5.7236. Min Range: -5.7236

Max Act: 4.2404. Min Act: -0.0000

Data Index: 1072471 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 5.7236. Min Range: -5.7236

Max Act: 4.3294. Min Act: -0.0000

Data Index: 1540205 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 5.7236. Min Range: -5.7236

Max Act: 3.9799. Min Act: -0.0000

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 5.7236. Min Range: -5.7236

Max Act: 4.0499. Min Act: -0.0000

Data Index: 1368064 (Python Code)

Max Activating Token Index: 166

Text #13

Max Range: 5.7236. Min Range: -5.7236

Max Act: 3.7686. Min Act: -0.0000

Data Index: 1597039 (Python Code)

Max Activating Token Index: 683

Text #14

Max Range: 5.7236. Min Range: -5.7236

Max Act: 3.7624. Min Act: -0.0000

Data Index: 1470317 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 5.7236. Min Range: -5.7236

Max Act: 3.9018. Min Act: -0.0000

Data Index: 1568104 (Python Code)

Max Activating Token Index: 486

Text #16

Max Range: 5.7236. Min Range: -5.7236

Max Act: 3.9115. Min Act: 0.0000

Data Index: 1646241 (Python Code)

Max Activating Token Index: 338

Text #17

Max Range: 5.7236. Min Range: -5.7236

Max Act: 3.9961. Min Act: -0.0000

Data Index: 1403131 (Python Code)

Max Activating Token Index: 636

Text #18

Max Range: 5.7236. Min Range: -5.7236

Max Act: 3.4596. Min Act: -0.0000

Data Index: 300954 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 5.7236. Min Range: -5.7236

Max Act: 3.8706. Min Act: -0.0000

Data Index: 1587486 (Python Code)

Max Activating Token Index: 16