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

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

Neuron 2591 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: 0.8858. Min Range: -0.8858

Max Act: 0.8858. Min Act: -0.0002

Data Index: 1139136 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.7050. Min Act: -0.0002

Data Index: 510932 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.7481. Min Act: -0.0002

Data Index: 666185 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.7226. Min Act: -0.0002

Data Index: 571594 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.7284. Min Act: -0.0002

Data Index: 501910 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6495. Min Act: -0.0002

Data Index: 119214 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.7662. Min Act: -0.0002

Data Index: 826299 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6663. Min Act: -0.0002

Data Index: 284978 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6929. Min Act: -0.0002

Data Index: 986408 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.7174. Min Act: -0.0002

Data Index: 767189 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6619. Min Act: -0.0002

Data Index: 148032 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.7140. Min Act: -0.0002

Data Index: 284559 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6987. Min Act: -0.0002

Data Index: 753137 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5782. Min Act: -0.0002

Data Index: 738259 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6449. Min Act: -0.0002

Data Index: 854441 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6076. Min Act: -0.0002

Data Index: 212268 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.7643. Min Act: -0.0002

Data Index: 641058 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6782. Min Act: -0.0002

Data Index: 476858 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6834. Min Act: -0.0002

Data Index: 1149904 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6691. Min Act: -0.0002

Data Index: 124955 (C4 (Web Text))

Max Activating Token Index: 272