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

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

Neuron 2678 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1216. Min Act: -0.0001

Data Index: 621759 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1209319 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1172. Min Act: -0.0001

Data Index: 541225 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1106. Min Act: -0.0001

Data Index: 343588 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1259. Min Act: -0.0001

Data Index: 92055 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1022414 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1323. Min Act: -0.0001

Data Index: 962355 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1143. Min Act: -0.0001

Data Index: 700016 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1170. Min Act: -0.0001

Data Index: 268833 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1048. Min Act: -0.0001

Data Index: 446592 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1089. Min Act: -0.0001

Data Index: 300624 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1124. Min Act: -0.0001

Data Index: 176936 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0914. Min Act: -0.0001

Data Index: 188132 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1040. Min Act: -0.0001

Data Index: 704302 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1134. Min Act: -0.0001

Data Index: 843413 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1040. Min Act: -0.0001

Data Index: 175973 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1061. Min Act: -0.0001

Data Index: 824225 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1128. Min Act: -0.0001

Data Index: 931273 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1036. Min Act: -0.0001

Data Index: 974996 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1028. Min Act: -0.0001

Data Index: 717737 (C4 (Web Text))

Max Activating Token Index: 311