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

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

Neuron 4428 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0002

Data Index: 893004 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0002

Data Index: 617276 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1044429 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0063. Min Act: -0.0002

Data Index: 591332 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1333817 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0063. Min Act: -0.0002

Data Index: 480607 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1175566 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1262601 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0061. Min Act: -0.0002

Data Index: 189957 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0060. Min Act: -0.0002

Data Index: 296261 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0060. Min Act: -0.0002

Data Index: 757415 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1156769 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0060. Min Act: -0.0002

Data Index: 816016 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0060. Min Act: -0.0002

Data Index: 348352 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0002

Data Index: 650426 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1323358 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0002

Data Index: 779046 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1140740 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0002

Data Index: 246350 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0002

Data Index: 419491 (C4 (Web Text))

Max Activating Token Index: 83