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

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

Neuron 3917 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1186997 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1521925 (Python Code)

Max Activating Token Index: 443

Text #2

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1654262 (Python Code)

Max Activating Token Index: 536

Text #3

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4727. Min Act: -0.0000

Data Index: 242569 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1531543 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1516361 (Python Code)

Max Activating Token Index: 482

Text #6

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1591107 (Python Code)

Max Activating Token Index: 744

Text #7

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1140191 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1581694 (Python Code)

Max Activating Token Index: 321

Text #9

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1558539 (Python Code)

Max Activating Token Index: 954

Text #10

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1517911 (Python Code)

Max Activating Token Index: 388

Text #11

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1635804 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1503859 (Python Code)

Max Activating Token Index: 289

Text #13

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1494964 (Python Code)

Max Activating Token Index: 695

Text #14

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1595307 (Python Code)

Max Activating Token Index: 453

Text #15

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1598944 (Python Code)

Max Activating Token Index: 1011

Text #16

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1482049 (Python Code)

Max Activating Token Index: 49

Text #17

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3772. Min Act: -0.0000

Data Index: 450563 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1390259 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1622878 (Python Code)

Max Activating Token Index: 386