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

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

Neuron 222 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: 1.8048. Min Range: -1.8048

Max Act: 1.7648. Min Act: -0.0000

Data Index: 1430918 (Python Code)

Max Activating Token Index: 432

Text #1

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5573. Min Act: -0.0000

Data Index: 952149 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.6162. Min Act: -0.0000

Data Index: 837319 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.8048. Min Act: -0.0000

Data Index: 53954 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.7020. Min Act: -0.0000

Data Index: 1613260 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5975. Min Act: -0.0000

Data Index: 248433 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5901. Min Act: -0.0000

Data Index: 848521 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.7807. Min Act: -0.0000

Data Index: 860492 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.6866. Min Act: -0.0000

Data Index: 178822 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.6746. Min Act: -0.0000

Data Index: 1088483 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.6620. Min Act: -0.0000

Data Index: 1014067 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.7340. Min Act: -0.0000

Data Index: 1476962 (Python Code)

Max Activating Token Index: 889

Text #12

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.6250. Min Act: -0.0000

Data Index: 1506829 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5290. Min Act: -0.0000

Data Index: 70995 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.6209. Min Act: -0.0000

Data Index: 478195 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5151. Min Act: -0.0000

Data Index: 1055261 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5953. Min Act: -0.0000

Data Index: 1508335 (Python Code)

Max Activating Token Index: 443

Text #17

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5719. Min Act: -0.0000

Data Index: 401912 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.6397. Min Act: -0.0000

Data Index: 1329867 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5415. Min Act: -0.0000

Data Index: 805215 (C4 (Web Text))

Max Activating Token Index: 388