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

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

Neuron 438 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0921. Min Act: -0.0002

Data Index: 339375 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0939. Min Act: -0.0002

Data Index: 481368 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0855. Min Act: -0.0002

Data Index: 697419 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0836. Min Act: -0.0002

Data Index: 796472 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0811. Min Act: -0.0002

Data Index: 258825 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0818. Min Act: -0.0002

Data Index: 367128 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0775. Min Act: -0.0002

Data Index: 347037 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0780. Min Act: -0.0002

Data Index: 252146 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1218175 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0747. Min Act: -0.0002

Data Index: 646128 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1307770 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0764. Min Act: -0.0002

Data Index: 2710 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1352636 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0732. Min Act: -0.0002

Data Index: 298232 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0797. Min Act: -0.0002

Data Index: 141871 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0730. Min Act: -0.0002

Data Index: 78480 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1113798 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0763. Min Act: -0.0002

Data Index: 103797 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0752. Min Act: -0.0002

Data Index: 431168 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0741. Min Act: -0.0002

Data Index: 322459 (C4 (Web Text))

Max Activating Token Index: 729