Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 559 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0004

Data Index: 674667 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 459917 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1215456 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0004

Data Index: 1156146 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0004

Data Index: 86881 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0004

Data Index: 503115 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0004

Data Index: 639329 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0004

Data Index: 805360 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0004

Data Index: 17984 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0004

Data Index: 245084 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0004

Data Index: 108008 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0004

Data Index: 565105 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0004

Data Index: 1275902 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0004

Data Index: 598849 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0004

Data Index: 103439 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0004

Data Index: 398433 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0004

Data Index: 958026 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0004

Data Index: 409793 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0004

Data Index: 202765 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0004

Data Index: 256945 (C4 (Web Text))

Max Activating Token Index: 913