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

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

Neuron 902 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3618. Min Range: -2.3618

Max Act: 2.3618. Min Act: -0.0000

Data Index: 1523922 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.9562. Min Act: -0.0000

Data Index: 1494567 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.5865. Min Act: -0.0000

Data Index: 1566289 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.4975. Min Act: -0.0000

Data Index: 1536486 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.5553. Min Act: -0.0000

Data Index: 1563208 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.4435. Min Act: -0.0000

Data Index: 1628599 (Python Code)

Max Activating Token Index: 395

Text #6

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.4251. Min Act: -0.0000

Data Index: 1465588 (Python Code)

Max Activating Token Index: 957

Text #7

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.3892. Min Act: -0.0000

Data Index: 1431592 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.2233. Min Act: -0.0000

Data Index: 407720 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.2798. Min Act: -0.0000

Data Index: 1597840 (Python Code)

Max Activating Token Index: 67

Text #10

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1495885 (Python Code)

Max Activating Token Index: 150

Text #11

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.2056. Min Act: -0.0000

Data Index: 1407501 (Python Code)

Max Activating Token Index: 423

Text #12

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.1822. Min Act: -0.0000

Data Index: 1471140 (Python Code)

Max Activating Token Index: 191

Text #13

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1132042 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.1368. Min Act: -0.0000

Data Index: 1096389 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.1396. Min Act: -0.0000

Data Index: 354364 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.1615. Min Act: -0.0000

Data Index: 194363 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.1820. Min Act: -0.0000

Data Index: 820787 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.1827. Min Act: -0.0000

Data Index: 1630365 (Python Code)

Max Activating Token Index: 198

Text #19

Max Range: 2.3618. Min Range: -2.3618

Max Act: 1.1826. Min Act: -0.0000

Data Index: 1601133 (Python Code)

Max Activating Token Index: 79