Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 955 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0065. Min Act: -0.0006

Data Index: 396213 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0065. Min Act: -0.0006

Data Index: 232533 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0064. Min Act: -0.0006

Data Index: 135543 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0064. Min Act: -0.0005

Data Index: 338495 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1221046 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0064. Min Act: -0.0005

Data Index: 562355 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1055975 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1161497 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0062. Min Act: -0.0005

Data Index: 884483 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0064. Min Act: -0.0005

Data Index: 1096433 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1116630 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0063. Min Act: -0.0006

Data Index: 522737 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1322582 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0063. Min Act: -0.0005

Data Index: 337164 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0062. Min Act: -0.0006

Data Index: 861988 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0062. Min Act: -0.0005

Data Index: 713829 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0062. Min Act: -0.0005

Data Index: 663857 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0062. Min Act: -0.0005

Data Index: 615862 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0062. Min Act: -0.0005

Data Index: 764004 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0060. Min Act: -0.0005

Data Index: 1110604 (C4 (Web Text))

Max Activating Token Index: 834