Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 627 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1521615 (Python Code)

Max Activating Token Index: 861

Text #1

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1558222 (Python Code)

Max Activating Token Index: 308

Text #2

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1377278 (Python Code)

Max Activating Token Index: 624

Text #3

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1475841 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1652197 (Python Code)

Max Activating Token Index: 753

Text #5

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1374434 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1582981 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1395128 (Python Code)

Max Activating Token Index: 449

Text #8

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1435077 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1641772 (Python Code)

Max Activating Token Index: 413

Text #10

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1560199 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1402455 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1572031 (Python Code)

Max Activating Token Index: 407

Text #13

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5761. Min Act: -0.0000

Data Index: 139518 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1527649 (Python Code)

Max Activating Token Index: 933

Text #15

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1544943 (Python Code)

Max Activating Token Index: 245

Text #16

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1597447 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1369336 (Python Code)

Max Activating Token Index: 428

Text #18

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1444960 (Python Code)

Max Activating Token Index: 369

Text #19

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1051712 (C4 (Web Text))

Max Activating Token Index: 25