Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1831 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.3979. Min Act: -0.0000

Data Index: 1369516 (Python Code)

Max Activating Token Index: 424

Text #1

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1583040 (Python Code)

Max Activating Token Index: 64

Text #2

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1619572 (Python Code)

Max Activating Token Index: 74

Text #3

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1360. Min Act: -0.0001

Data Index: 1540131 (Python Code)

Max Activating Token Index: 423

Text #4

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0825. Min Act: -0.0000

Data Index: 241313 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.8926. Min Act: -0.0000

Data Index: 110618 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1278007 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0382. Min Act: -0.0000

Data Index: 197527 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1200. Min Act: -0.0000

Data Index: 467360 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1032. Min Act: -0.0001

Data Index: 1561517 (Python Code)

Max Activating Token Index: 433

Text #10

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1095. Min Act: -0.0000

Data Index: 388060 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1673. Min Act: -0.0000

Data Index: 773752 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0221. Min Act: -0.0000

Data Index: 187660 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0231. Min Act: -0.0000

Data Index: 238362 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1180467 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9558. Min Act: -0.0000

Data Index: 494730 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9907. Min Act: -0.0000

Data Index: 526753 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0775. Min Act: -0.0000

Data Index: 904995 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0032. Min Act: -0.0000

Data Index: 247859 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1225298 (C4 (Web Text))

Max Activating Token Index: 188