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

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

Neuron 2200 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: 0.1102. Min Range: -0.1102

Max Act: 0.1102. Min Act: -0.0000

Data Index: 538507 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1263448 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0964. Min Act: -0.0000

Data Index: 419002 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1357615 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1243021 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0892. Min Act: -0.0001

Data Index: 742492 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0906. Min Act: -0.0001

Data Index: 650310 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1091259 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0874. Min Act: -0.0000

Data Index: 610536 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0863. Min Act: -0.0001

Data Index: 636864 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0824. Min Act: -0.0001

Data Index: 65061 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0832. Min Act: -0.0001

Data Index: 461150 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1423178 (Python Code)

Max Activating Token Index: 446

Text #13

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1104149 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1362805 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1317350 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1524424 (Python Code)

Max Activating Token Index: 377

Text #17

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0749. Min Act: -0.0001

Data Index: 388351 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0773. Min Act: -0.0001

Data Index: 289426 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0787. Min Act: -0.0001

Data Index: 58392 (C4 (Web Text))

Max Activating Token Index: 255