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

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

Neuron 3104 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0096. Min Act: -0.0000

Data Index: 1565807 (Python Code)

Max Activating Token Index: 333

Text #1

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0078. Min Act: -0.0001

Data Index: 1618934 (Python Code)

Max Activating Token Index: 319

Text #2

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0080. Min Act: -0.0000

Data Index: 179408 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0076. Min Act: -0.0000

Data Index: 524919 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0076. Min Act: 0.0000

Data Index: 1501998 (Python Code)

Max Activating Token Index: 418

Text #5

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0076. Min Act: 0.0000

Data Index: 894494 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0073. Min Act: 0.0000

Data Index: 1402779 (Python Code)

Max Activating Token Index: 338

Text #7

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0075. Min Act: 0.0000

Data Index: 1588786 (Python Code)

Max Activating Token Index: 360

Text #8

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0075. Min Act: 0.0000

Data Index: 1490893 (Python Code)

Max Activating Token Index: 354

Text #9

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0074. Min Act: -0.0000

Data Index: 1191808 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0072. Min Act: 0.0000

Data Index: 1598843 (Python Code)

Max Activating Token Index: 349

Text #11

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0074. Min Act: 0.0001

Data Index: 1590863 (Python Code)

Max Activating Token Index: 279

Text #12

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0074. Min Act: 0.0000

Data Index: 1582374 (Python Code)

Max Activating Token Index: 384

Text #13

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0077. Min Act: -0.0000

Data Index: 1455219 (Python Code)

Max Activating Token Index: 390

Text #14

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0074. Min Act: 0.0000

Data Index: 401854 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0072. Min Act: -0.0000

Data Index: 1093465 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0073. Min Act: 0.0000

Data Index: 1478225 (Python Code)

Max Activating Token Index: 409

Text #17

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0073. Min Act: 0.0000

Data Index: 1034618 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0073. Min Act: -0.0000

Data Index: 1634873 (Python Code)

Max Activating Token Index: 423

Text #19

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0076. Min Act: -0.0000

Data Index: 311856 (C4 (Web Text))

Max Activating Token Index: 442