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

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

Neuron 1684 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: 0.1199. Min Range: -0.1199

Max Act: 0.1199. Min Act: -0.0004

Data Index: 482777 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1102. Min Act: -0.0003

Data Index: 80008 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1090. Min Act: -0.0003

Data Index: 201572 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1030. Min Act: -0.0004

Data Index: 1181538 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1008. Min Act: -0.0004

Data Index: 904423 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1022. Min Act: -0.0003

Data Index: 1062516 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0964. Min Act: -0.0003

Data Index: 89 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1010. Min Act: -0.0003

Data Index: 1180986 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1012. Min Act: -0.0002

Data Index: 760191 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0992. Min Act: -0.0003

Data Index: 176116 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0969. Min Act: -0.0003

Data Index: 1261445 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0974. Min Act: -0.0003

Data Index: 931390 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0955. Min Act: -0.0003

Data Index: 342946 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0945. Min Act: -0.0003

Data Index: 724170 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0993. Min Act: -0.0004

Data Index: 1178265 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0948. Min Act: -0.0003

Data Index: 1057688 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0990. Min Act: -0.0003

Data Index: 136861 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0994. Min Act: -0.0003

Data Index: 267716 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0945. Min Act: -0.0003

Data Index: 575173 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1009. Min Act: -0.0004

Data Index: 102919 (C4 (Web Text))

Max Activating Token Index: 323