Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 260 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1521417 (Python Code)

Max Activating Token Index: 286

Text #1

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1935. Min Act: 0.0000

Data Index: 1546731 (Python Code)

Max Activating Token Index: 685

Text #2

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1032731 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1058466 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1249321 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1853. Min Act: -0.0001

Data Index: 1590434 (Python Code)

Max Activating Token Index: 303

Text #6

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1630679 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1816. Min Act: 0.0000

Data Index: 1534901 (Python Code)

Max Activating Token Index: 37

Text #8

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1802. Min Act: -0.0001

Data Index: 432239 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1700. Min Act: -0.0001

Data Index: 1344952 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1748. Min Act: -0.0001

Data Index: 1017513 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1676. Min Act: -0.0001

Data Index: 599906 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1671. Min Act: -0.0001

Data Index: 984249 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1701. Min Act: 0.0000

Data Index: 1374628 (Python Code)

Max Activating Token Index: 364

Text #14

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1342288 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1631. Min Act: -0.0001

Data Index: 254823 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1260103 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1660. Min Act: -0.0001

Data Index: 449029 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1583. Min Act: -0.0001

Data Index: 1598015 (Python Code)

Max Activating Token Index: 627

Text #19

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1384163 (Python Code)

Max Activating Token Index: 221