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

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

Neuron 2865 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.8109. Min Act: -0.0001

Data Index: 379072 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.6267. Min Act: -0.0001

Data Index: 1243353 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.6643. Min Act: -0.0001

Data Index: 1036277 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.5338. Min Act: -0.0001

Data Index: 52772 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.6216. Min Act: -0.0001

Data Index: 397879 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.5888. Min Act: -0.0001

Data Index: 407062 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.4449. Min Act: -0.0001

Data Index: 1038828 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.5257. Min Act: -0.0001

Data Index: 1234957 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.3717. Min Act: -0.0001

Data Index: 1317104 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.3217. Min Act: -0.0001

Data Index: 1071298 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.4986. Min Act: -0.0001

Data Index: 648047 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.3634. Min Act: -0.0001

Data Index: 1265960 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.3449. Min Act: -0.0001

Data Index: 802351 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.3005. Min Act: -0.0001

Data Index: 1158043 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.3384. Min Act: -0.0001

Data Index: 1091047 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.3545. Min Act: -0.0001

Data Index: 707651 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.2339. Min Act: -0.0001

Data Index: 1210698 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.3887. Min Act: -0.0001

Data Index: 349760 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.3979. Min Act: -0.0001

Data Index: 1135912 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.8109. Min Range: -1.8109

Max Act: 1.3139. Min Act: -0.0001

Data Index: 1257814 (C4 (Web Text))

Max Activating Token Index: 716