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

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

Neuron 2514 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1661. Min Act: -0.0003

Data Index: 1266337 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1513. Min Act: -0.0003

Data Index: 537162 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1337. Min Act: -0.0003

Data Index: 774179 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1229. Min Act: -0.0003

Data Index: 1048975 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1304. Min Act: -0.0003

Data Index: 54555 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1102. Min Act: -0.0003

Data Index: 207815 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1095. Min Act: -0.0003

Data Index: 60196 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1101. Min Act: -0.0003

Data Index: 885409 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1060. Min Act: -0.0003

Data Index: 1349545 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1034. Min Act: -0.0003

Data Index: 30127 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1060. Min Act: -0.0003

Data Index: 357803 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1017. Min Act: -0.0003

Data Index: 229834 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1455093 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.0971. Min Act: -0.0003

Data Index: 1276864 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.0960. Min Act: -0.0003

Data Index: 421826 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.0980. Min Act: -0.0003

Data Index: 853261 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.0970. Min Act: -0.0003

Data Index: 1785 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.0959. Min Act: -0.0003

Data Index: 1102515 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.0922. Min Act: -0.0003

Data Index: 204934 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.0952. Min Act: -0.0002

Data Index: 133239 (C4 (Web Text))

Max Activating Token Index: 580