Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 360 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.1022. Min Act: -0.0005

Data Index: 1433874 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0985. Min Act: -0.0005

Data Index: 1644393 (Python Code)

Max Activating Token Index: 881

Text #2

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0788. Min Act: -0.0005

Data Index: 1565672 (Python Code)

Max Activating Token Index: 723

Text #3

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0688. Min Act: -0.0005

Data Index: 1431905 (Python Code)

Max Activating Token Index: 1010

Text #4

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0576. Min Act: -0.0005

Data Index: 356802 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0563. Min Act: -0.0004

Data Index: 1367300 (Python Code)

Max Activating Token Index: 954

Text #6

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0543. Min Act: -0.0005

Data Index: 456377 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0556. Min Act: -0.0004

Data Index: 1307894 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0522. Min Act: -0.0005

Data Index: 1488549 (Python Code)

Max Activating Token Index: 671

Text #9

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0510. Min Act: -0.0005

Data Index: 1574022 (Python Code)

Max Activating Token Index: 987

Text #10

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0486. Min Act: -0.0005

Data Index: 1555591 (Python Code)

Max Activating Token Index: 974

Text #11

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0482. Min Act: -0.0005

Data Index: 1403468 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0469. Min Act: -0.0005

Data Index: 289933 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0476. Min Act: -0.0005

Data Index: 1513650 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0475. Min Act: -0.0005

Data Index: 1292473 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0465. Min Act: -0.0005

Data Index: 1561821 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0473. Min Act: -0.0005

Data Index: 1407896 (Python Code)

Max Activating Token Index: 867

Text #17

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0470. Min Act: -0.0005

Data Index: 1602932 (Python Code)

Max Activating Token Index: 994

Text #18

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0478. Min Act: -0.0005

Data Index: 764921 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0465. Min Act: -0.0005

Data Index: 16629 (C4 (Web Text))

Max Activating Token Index: 834