Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 230 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1191. Min Act: -0.0004

Data Index: 1217950 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1198. Min Act: -0.0003

Data Index: 355543 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1039. Min Act: -0.0003

Data Index: 916156 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1058. Min Act: -0.0003

Data Index: 262775 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1091. Min Act: -0.0003

Data Index: 362642 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1025. Min Act: -0.0003

Data Index: 509819 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1036. Min Act: -0.0003

Data Index: 255042 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1088. Min Act: -0.0003

Data Index: 156852 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1033. Min Act: -0.0003

Data Index: 905871 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1005. Min Act: -0.0003

Data Index: 761283 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1033. Min Act: -0.0003

Data Index: 1168972 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1013. Min Act: -0.0003

Data Index: 689818 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1014. Min Act: -0.0003

Data Index: 995520 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1053. Min Act: -0.0003

Data Index: 547498 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1021. Min Act: -0.0003

Data Index: 167653 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1020. Min Act: -0.0003

Data Index: 378926 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1005. Min Act: -0.0003

Data Index: 33253 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1008. Min Act: -0.0003

Data Index: 1086990 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0959. Min Act: -0.0003

Data Index: 1103573 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1003. Min Act: -0.0003

Data Index: 1111380 (C4 (Web Text))

Max Activating Token Index: 234