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

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

Neuron 3635 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7180. Min Range: -3.7180

Max Act: 3.7180. Min Act: -0.0000

Data Index: 1532914 (Python Code)

Max Activating Token Index: 395

Text #1

Max Range: 3.7180. Min Range: -3.7180

Max Act: 3.1993. Min Act: -0.0000

Data Index: 1474301 (Python Code)

Max Activating Token Index: 604

Text #2

Max Range: 3.7180. Min Range: -3.7180

Max Act: 3.0257. Min Act: -0.0000

Data Index: 1513586 (Python Code)

Max Activating Token Index: 142

Text #3

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.8133. Min Act: -0.0000

Data Index: 1443182 (Python Code)

Max Activating Token Index: 232

Text #4

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.5414. Min Act: -0.0000

Data Index: 1460473 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.7586. Min Act: -0.0000

Data Index: 1476996 (Python Code)

Max Activating Token Index: 621

Text #6

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.7601. Min Act: -0.0000

Data Index: 1435828 (Python Code)

Max Activating Token Index: 605

Text #7

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.8018. Min Act: -0.0000

Data Index: 1503575 (Python Code)

Max Activating Token Index: 959

Text #8

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.6052. Min Act: -0.0000

Data Index: 1540711 (Python Code)

Max Activating Token Index: 566

Text #9

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.3387. Min Act: -0.0000

Data Index: 1645481 (Python Code)

Max Activating Token Index: 490

Text #10

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.2964. Min Act: -0.0000

Data Index: 1443314 (Python Code)

Max Activating Token Index: 360

Text #11

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.3204. Min Act: -0.0000

Data Index: 1639665 (Python Code)

Max Activating Token Index: 971

Text #12

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.3037. Min Act: -0.0000

Data Index: 1594591 (Python Code)

Max Activating Token Index: 604

Text #13

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.1607. Min Act: -0.0000

Data Index: 1410581 (Python Code)

Max Activating Token Index: 400

Text #14

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.1454. Min Act: -0.0000

Data Index: 1603384 (Python Code)

Max Activating Token Index: 209

Text #15

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.0714. Min Act: -0.0000

Data Index: 1397572 (Python Code)

Max Activating Token Index: 928

Text #16

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.1716. Min Act: -0.0000

Data Index: 1495502 (Python Code)

Max Activating Token Index: 338

Text #17

Max Range: 3.7180. Min Range: -3.7180

Max Act: 2.1671. Min Act: -0.0000

Data Index: 1516635 (Python Code)

Max Activating Token Index: 215

Text #18

Max Range: 3.7180. Min Range: -3.7180

Max Act: 1.9146. Min Act: -0.0000

Data Index: 1463097 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 3.7180. Min Range: -3.7180

Max Act: 1.8969. Min Act: -0.0000

Data Index: 1462574 (Python Code)

Max Activating Token Index: 749