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

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

Neuron 219 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0001

Data Index: 871415 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1247634 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1034553 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0810. Min Act: -0.0001

Data Index: 447632 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1574570 (Python Code)

Max Activating Token Index: 380

Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0813. Min Act: -0.0001

Data Index: 512866 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0799. Min Act: -0.0002

Data Index: 43732 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0810. Min Act: -0.0001

Data Index: 280934 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0805. Min Act: -0.0002

Data Index: 114287 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0813. Min Act: -0.0001

Data Index: 951531 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1146037 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0782. Min Act: -0.0001

Data Index: 359778 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0789. Min Act: -0.0001

Data Index: 530992 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0781. Min Act: -0.0001

Data Index: 624796 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1325765 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0782. Min Act: -0.0001

Data Index: 419286 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0783. Min Act: -0.0001

Data Index: 142423 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0773. Min Act: -0.0001

Data Index: 850428 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1452669 (Python Code)

Max Activating Token Index: 452

Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1113337 (C4 (Web Text))

Max Activating Token Index: 654