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

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

Neuron 790 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: 1.9696. Min Range: -1.9696

Max Act: 1.9696. Min Act: -0.0003

Data Index: 1323686 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.7342. Min Act: -0.0002

Data Index: 1187213 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.5751. Min Act: -0.0002

Data Index: 1100030 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.4442. Min Act: -0.0003

Data Index: 165924 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.4593. Min Act: -0.0002

Data Index: 969197 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.4067. Min Act: -0.0003

Data Index: 504135 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.3955. Min Act: -0.0003

Data Index: 1209262 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.4264. Min Act: -0.0002

Data Index: 810679 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2889. Min Act: -0.0003

Data Index: 824182 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2736. Min Act: -0.0002

Data Index: 1070858 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.3050. Min Act: -0.0003

Data Index: 495072 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.3051. Min Act: -0.0003

Data Index: 820416 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2777. Min Act: -0.0002

Data Index: 1164887 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2748. Min Act: -0.0003

Data Index: 464366 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2591. Min Act: -0.0002

Data Index: 689183 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2322. Min Act: -0.0002

Data Index: 931669 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.1941. Min Act: -0.0002

Data Index: 366532 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2593. Min Act: -0.0003

Data Index: 904206 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2693. Min Act: -0.0002

Data Index: 93924 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.2575. Min Act: -0.0002

Data Index: 241232 (C4 (Web Text))

Max Activating Token Index: 119