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

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

Neuron 1024 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: 0.0077. Min Range: -0.0077

Max Act: 0.0077. Min Act: -0.0005

Data Index: 975930 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0077. Min Act: -0.0005

Data Index: 1256292 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0071. Min Act: -0.0005

Data Index: 120175 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1203693 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0071. Min Act: -0.0006

Data Index: 345949 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0005

Data Index: 768753 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0005

Data Index: 754312 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0005

Data Index: 846905 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0005

Data Index: 1335963 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0005

Data Index: 57716 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0005

Data Index: 307635 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0005

Data Index: 185451 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0005

Data Index: 1265295 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0005

Data Index: 245772 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0005

Data Index: 142030 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0005

Data Index: 74928 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0064. Min Act: -0.0005

Data Index: 162384 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0064. Min Act: -0.0005

Data Index: 695334 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0064. Min Act: -0.0005

Data Index: 970289 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0064. Min Act: -0.0005

Data Index: 49889 (C4 (Web Text))

Max Activating Token Index: 235