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

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

Neuron 5432 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: 0.6078. Min Range: -0.6078

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1538619 (Python Code)

Max Activating Token Index: 223

Text #1

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1452589 (Python Code)

Max Activating Token Index: 755

Text #2

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1371534 (Python Code)

Max Activating Token Index: 932

Text #3

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1472123 (Python Code)

Max Activating Token Index: 915

Text #4

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1594853 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1362472 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1500994 (Python Code)

Max Activating Token Index: 982

Text #7

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1388505 (Python Code)

Max Activating Token Index: 1003

Text #8

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1596598 (Python Code)

Max Activating Token Index: 425

Text #9

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1427658 (Python Code)

Max Activating Token Index: 338

Text #10

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1551772 (Python Code)

Max Activating Token Index: 955

Text #11

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1596580 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1494019 (Python Code)

Max Activating Token Index: 165

Text #13

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1455424 (Python Code)

Max Activating Token Index: 131

Text #14

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1534955 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1635307 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1505198 (Python Code)

Max Activating Token Index: 387

Text #17

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1558782 (Python Code)

Max Activating Token Index: 88

Text #18

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1465373 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 0.6078. Min Range: -0.6078

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1572388 (Python Code)

Max Activating Token Index: 952