Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1629 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1188616 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1377. Min Act: -0.0002

Data Index: 476526 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1339. Min Act: -0.0002

Data Index: 547219 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1222. Min Act: -0.0002

Data Index: 693131 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1125. Min Act: -0.0002

Data Index: 796475 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1147. Min Act: -0.0002

Data Index: 819717 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1105. Min Act: -0.0002

Data Index: 1163751 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1043. Min Act: -0.0002

Data Index: 935415 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1036. Min Act: -0.0002

Data Index: 476046 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1067. Min Act: -0.0002

Data Index: 742827 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1045. Min Act: -0.0002

Data Index: 250457 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1023. Min Act: -0.0002

Data Index: 413133 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1021. Min Act: -0.0002

Data Index: 580115 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1017. Min Act: -0.0002

Data Index: 853360 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0994. Min Act: -0.0002

Data Index: 890033 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1029. Min Act: -0.0002

Data Index: 589287 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0990. Min Act: -0.0002

Data Index: 121785 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1006. Min Act: -0.0002

Data Index: 134795 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0991. Min Act: -0.0002

Data Index: 757282 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0981. Min Act: -0.0002

Data Index: 216395 (C4 (Web Text))

Max Activating Token Index: 603