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

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

Neuron 2772 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.8697. Min Act: -0.0000

Data Index: 626451 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.5311. Min Act: -0.0000

Data Index: 1205773 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.4830. Min Act: -0.0000

Data Index: 26833 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.3251. Min Act: -0.0000

Data Index: 358695 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.2255. Min Act: -0.0000

Data Index: 1323871 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1014367 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.2242. Min Act: -0.0000

Data Index: 691953 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.1831. Min Act: -0.0000

Data Index: 1638342 (Python Code)

Max Activating Token Index: 724

Text #8

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.1057. Min Act: -0.0000

Data Index: 659857 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.0760. Min Act: -0.0000

Data Index: 582231 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.1788. Min Act: -0.0000

Data Index: 304563 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1124110 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1317545 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1268717 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.1951. Min Act: -0.0000

Data Index: 1257649 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.0976. Min Act: -0.0000

Data Index: 1320558 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.0585. Min Act: -0.0000

Data Index: 1225190 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.0254. Min Act: -0.0000

Data Index: 799283 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.0680. Min Act: -0.0000

Data Index: 150308 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.1013. Min Act: -0.0000

Data Index: 562927 (C4 (Web Text))

Max Activating Token Index: 368