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

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

Neuron 3377 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.8367. Min Act: -0.0001

Data Index: 1592599 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7351. Min Act: -0.0001

Data Index: 1413069 (Python Code)

Max Activating Token Index: 419

Text #2

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7612. Min Act: -0.0001

Data Index: 1489751 (Python Code)

Max Activating Token Index: 151

Text #3

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7596. Min Act: -0.0001

Data Index: 1417433 (Python Code)

Max Activating Token Index: 710

Text #4

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6914. Min Act: -0.0001

Data Index: 1537601 (Python Code)

Max Activating Token Index: 772

Text #5

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6612. Min Act: -0.0001

Data Index: 1362401 (Python Code)

Max Activating Token Index: 848

Text #6

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6537. Min Act: -0.0001

Data Index: 1630788 (Python Code)

Max Activating Token Index: 881

Text #7

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6603. Min Act: -0.0001

Data Index: 1406402 (Python Code)

Max Activating Token Index: 378

Text #8

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6318. Min Act: -0.0001

Data Index: 1612219 (Python Code)

Max Activating Token Index: 131

Text #9

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5986. Min Act: -0.0001

Data Index: 1559220 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5984. Min Act: -0.0001

Data Index: 1370773 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6083. Min Act: -0.0001

Data Index: 1605014 (Python Code)

Max Activating Token Index: 511

Text #12

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6149. Min Act: -0.0001

Data Index: 1608132 (Python Code)

Max Activating Token Index: 665

Text #13

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1537795 (Python Code)

Max Activating Token Index: 891

Text #14

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1624365 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5570. Min Act: -0.0001

Data Index: 1493994 (Python Code)

Max Activating Token Index: 885

Text #16

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1469577 (Python Code)

Max Activating Token Index: 162

Text #17

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5473. Min Act: -0.0001

Data Index: 1401044 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1624963 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5944. Min Act: -0.0001

Data Index: 1458408 (Python Code)

Max Activating Token Index: 666