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

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

Neuron 2504 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1195993 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0129. Min Act: -0.0003

Data Index: 170720 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1105145 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1207709 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1351656 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0098. Min Act: -0.0003

Data Index: 144546 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1331499 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0099. Min Act: -0.0003

Data Index: 161032 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1231928 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0102. Min Act: -0.0002

Data Index: 702340 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0095. Min Act: -0.0002

Data Index: 394281 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0097. Min Act: -0.0003

Data Index: 739146 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0091. Min Act: -0.0002

Data Index: 846695 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0089. Min Act: -0.0002

Data Index: 912968 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0092. Min Act: -0.0003

Data Index: 746068 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0091. Min Act: -0.0003

Data Index: 569881 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0089. Min Act: -0.0003

Data Index: 814585 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0096. Min Act: -0.0002

Data Index: 741695 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1054028 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0085. Min Act: -0.0002

Data Index: 33360 (C4 (Web Text))

Max Activating Token Index: 541