Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2673 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1577313 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1281. Min Act: -0.0001

Data Index: 171004 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1233. Min Act: -0.0002

Data Index: 895395 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1222. Min Act: -0.0002

Data Index: 34612 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1244. Min Act: -0.0002

Data Index: 350334 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1068. Min Act: -0.0002

Data Index: 86314 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1616131 (Python Code)

Max Activating Token Index: 988

Text #7

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1401858 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1471486 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1480835 (Python Code)

Max Activating Token Index: 774

Text #10

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1011. Min Act: -0.0002

Data Index: 470538 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1041. Min Act: -0.0002

Data Index: 84305 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1606671 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1158. Min Act: -0.0002

Data Index: 930447 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1537857 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1534050 (Python Code)

Max Activating Token Index: 462

Text #16

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1027. Min Act: -0.0001

Data Index: 384832 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1075. Min Act: -0.0002

Data Index: 242685 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0948. Min Act: -0.0002

Data Index: 522912 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0948. Min Act: -0.0002

Data Index: 886343 (C4 (Web Text))

Max Activating Token Index: 763