Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3880 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1629105 (Python Code)

Max Activating Token Index: 989

Text #1

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1406521 (Python Code)

Max Activating Token Index: 394

Text #2

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1918. Min Act: 0.0000

Data Index: 1627120 (Python Code)

Max Activating Token Index: 537

Text #3

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1655805 (Python Code)

Max Activating Token Index: 999

Text #4

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1825. Min Act: -0.0000

Data Index: 275714 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1586644 (Python Code)

Max Activating Token Index: 681

Text #6

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1378970 (Python Code)

Max Activating Token Index: 302

Text #7

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1562665 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1448822 (Python Code)

Max Activating Token Index: 501

Text #9

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1406955 (Python Code)

Max Activating Token Index: 505

Text #10

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1506483 (Python Code)

Max Activating Token Index: 726

Text #11

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1468669 (Python Code)

Max Activating Token Index: 372

Text #12

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1661. Min Act: -0.0001

Data Index: 1398422 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1477937 (Python Code)

Max Activating Token Index: 1007

Text #14

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1644356 (Python Code)

Max Activating Token Index: 331

Text #15

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1516380 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1583246 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1447875 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1604. Min Act: -0.0001

Data Index: 834115 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1622. Min Act: 0.0000

Data Index: 1579067 (Python Code)

Max Activating Token Index: 76