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

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

Neuron 4282 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: 2.4795. Min Range: -2.4795

Max Act: 2.4795. Min Act: -0.0000

Data Index: 1539005 (Python Code)

Max Activating Token Index: 695

Text #1

Max Range: 2.4795. Min Range: -2.4795

Max Act: 2.0751. Min Act: -0.0000

Data Index: 1403268 (Python Code)

Max Activating Token Index: 678

Text #2

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.9738. Min Act: -0.0000

Data Index: 1360275 (Python Code)

Max Activating Token Index: 843

Text #3

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.8876. Min Act: -0.0000

Data Index: 1489340 (Python Code)

Max Activating Token Index: 144

Text #4

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.7059. Min Act: -0.0000

Data Index: 1519744 (Python Code)

Max Activating Token Index: 940

Text #5

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.6083. Min Act: -0.0000

Data Index: 1404774 (Python Code)

Max Activating Token Index: 897

Text #6

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.6071. Min Act: -0.0000

Data Index: 1637998 (Python Code)

Max Activating Token Index: 573

Text #7

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.6794. Min Act: -0.0000

Data Index: 1546738 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.5842. Min Act: -0.0000

Data Index: 1604456 (Python Code)

Max Activating Token Index: 722

Text #9

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1367394 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.5451. Min Act: -0.0000

Data Index: 1482018 (Python Code)

Max Activating Token Index: 929

Text #11

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1523228 (Python Code)

Max Activating Token Index: 795

Text #12

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.5097. Min Act: -0.0000

Data Index: 1468925 (Python Code)

Max Activating Token Index: 258

Text #13

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.4656. Min Act: -0.0000

Data Index: 1365975 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.4978. Min Act: -0.0000

Data Index: 1547771 (Python Code)

Max Activating Token Index: 939

Text #15

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.4685. Min Act: -0.0000

Data Index: 1406420 (Python Code)

Max Activating Token Index: 913

Text #16

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1607250 (Python Code)

Max Activating Token Index: 450

Text #17

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.5066. Min Act: -0.0000

Data Index: 1400625 (Python Code)

Max Activating Token Index: 308

Text #18

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.4578. Min Act: -0.0000

Data Index: 1649618 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 2.4795. Min Range: -2.4795

Max Act: 1.3984. Min Act: -0.0000

Data Index: 1648253 (Python Code)

Max Activating Token Index: 481