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

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

Neuron 3581 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1204035 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0947. Min Act: -0.0002

Data Index: 426618 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0997. Min Act: -0.0002

Data Index: 1325328 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0981. Min Act: -0.0002

Data Index: 950618 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0934. Min Act: -0.0002

Data Index: 981645 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1046137 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1392281 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0928. Min Act: -0.0002

Data Index: 767400 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0866. Min Act: -0.0002

Data Index: 282272 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0897. Min Act: -0.0002

Data Index: 226376 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1545355 (Python Code)

Max Activating Token Index: 901

Text #11

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0879. Min Act: -0.0002

Data Index: 356675 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0837. Min Act: -0.0002

Data Index: 259102 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0857. Min Act: -0.0002

Data Index: 84335 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1497979 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0855. Min Act: -0.0002

Data Index: 670544 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0826. Min Act: -0.0002

Data Index: 988001 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1404653 (Python Code)

Max Activating Token Index: 441

Text #18

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1237171 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1635610 (Python Code)

Max Activating Token Index: 984