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

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

Neuron 2125 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1504. Min Act: -0.0002

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1474. Min Act: -0.0002

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1233. Min Act: -0.0002

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1153. Min Act: -0.0002

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.0933. Min Act: -0.0002

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1025. Min Act: -0.0002

Data Index: 234120 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1256907 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.0923. Min Act: -0.0002

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.0921. Min Act: -0.0002

Data Index: 698780 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.0947. Min Act: -0.0002

Data Index: 66738 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.0909. Min Act: -0.0002

Data Index: 717486 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1010. Min Act: -0.0002

Data Index: 967090 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1255158 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.0906. Min Act: -0.0002

Data Index: 296406 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1021823 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.0880. Min Act: -0.0002

Data Index: 447176 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1130011 (C4 (Web Text))

Max Activating Token Index: 607