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

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

Neuron 3085 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: 0.5231. Min Range: -0.5231

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1430492 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1499621 (Python Code)

Max Activating Token Index: 361

Text #2

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1565007 (Python Code)

Max Activating Token Index: 961

Text #3

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1655810 (Python Code)

Max Activating Token Index: 614

Text #4

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1654100 (Python Code)

Max Activating Token Index: 317

Text #5

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1631012 (Python Code)

Max Activating Token Index: 733

Text #6

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1361747 (Python Code)

Max Activating Token Index: 302

Text #7

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1639551 (Python Code)

Max Activating Token Index: 289

Text #8

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4388. Min Act: -0.0000

Data Index: 366341 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1412473 (Python Code)

Max Activating Token Index: 759

Text #10

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1566666 (Python Code)

Max Activating Token Index: 782

Text #11

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1412873 (Python Code)

Max Activating Token Index: 965

Text #12

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1645751 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1497677 (Python Code)

Max Activating Token Index: 243

Text #14

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1396071 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1642804 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1383705 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1563728 (Python Code)

Max Activating Token Index: 58

Text #18

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1441970 (Python Code)

Max Activating Token Index: 350

Text #19

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1364480 (Python Code)

Max Activating Token Index: 344