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

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

Neuron 3900 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1570886 (Python Code)

Max Activating Token Index: 1000

Text #1

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1548975 (Python Code)

Max Activating Token Index: 854

Text #2

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1521183 (Python Code)

Max Activating Token Index: 408

Text #3

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1466090 (Python Code)

Max Activating Token Index: 875

Text #4

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1364481 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1641473 (Python Code)

Max Activating Token Index: 255

Text #6

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1537713 (Python Code)

Max Activating Token Index: 291

Text #7

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1491049 (Python Code)

Max Activating Token Index: 656

Text #8

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1413514 (Python Code)

Max Activating Token Index: 734

Text #9

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1585575 (Python Code)

Max Activating Token Index: 380

Text #10

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1646412 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1472825 (Python Code)

Max Activating Token Index: 157

Text #12

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1378658 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1395217 (Python Code)

Max Activating Token Index: 463

Text #14

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1450827 (Python Code)

Max Activating Token Index: 599

Text #15

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1578641 (Python Code)

Max Activating Token Index: 325

Text #16

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1505406 (Python Code)

Max Activating Token Index: 267

Text #17

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1436155 (Python Code)

Max Activating Token Index: 349

Text #18

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1580425 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1466391 (Python Code)

Max Activating Token Index: 427