Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2578 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1404. Min Act: -0.0001

Data Index: 853453 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1241. Min Act: -0.0001

Data Index: 545809 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1250. Min Act: -0.0001

Data Index: 754327 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1163. Min Act: -0.0001

Data Index: 713275 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1078. Min Act: -0.0001

Data Index: 849971 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1102. Min Act: -0.0001

Data Index: 402559 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1283282 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1077. Min Act: -0.0001

Data Index: 339820 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1038916 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1045728 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1022. Min Act: -0.0001

Data Index: 213469 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1015. Min Act: -0.0001

Data Index: 344635 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1227. Min Act: -0.0001

Data Index: 820387 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0969. Min Act: -0.0001

Data Index: 426925 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1610 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1029. Min Act: -0.0001

Data Index: 288974 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1133070 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1242196 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0984. Min Act: -0.0001

Data Index: 431041 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0974. Min Act: -0.0001

Data Index: 149631 (C4 (Web Text))

Max Activating Token Index: 496