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

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

Neuron 1042 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2855. Min Act: -0.0001

Data Index: 1468319 (Python Code)

Max Activating Token Index: 295

Text #1

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2109. Min Act: -0.0001

Data Index: 600464 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1799. Min Act: -0.0000

Data Index: 921227 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1902. Min Act: -0.0000

Data Index: 77081 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1544660 (Python Code)

Max Activating Token Index: 61

Text #5

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1669. Min Act: -0.0000

Data Index: 783499 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1922. Min Act: -0.0001

Data Index: 727268 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1320773 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1607. Min Act: -0.0001

Data Index: 1516221 (Python Code)

Max Activating Token Index: 844

Text #9

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1526. Min Act: -0.0000

Data Index: 702009 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1729. Min Act: -0.0000

Data Index: 235730 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1545. Min Act: -0.0001

Data Index: 439491 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1764. Min Act: -0.0000

Data Index: 368457 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1632. Min Act: -0.0001

Data Index: 731360 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1632. Min Act: -0.0001

Data Index: 1431158 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1522. Min Act: -0.0001

Data Index: 945603 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1745. Min Act: -0.0000

Data Index: 888744 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1470053 (Python Code)

Max Activating Token Index: 588

Text #18

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1626320 (Python Code)

Max Activating Token Index: 922

Text #19

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1363436 (Python Code)

Max Activating Token Index: 262