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

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

Neuron 1563 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1214356 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2721. Min Act: -0.0000

Data Index: 622785 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1257602 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2798. Min Act: -0.0000

Data Index: 354161 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1040941 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2525. Min Act: -0.0000

Data Index: 911509 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2398. Min Act: -0.0000

Data Index: 601882 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2254. Min Act: -0.0000

Data Index: 924027 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2284. Min Act: -0.0000

Data Index: 184126 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1295546 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2194. Min Act: -0.0000

Data Index: 224127 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2162. Min Act: -0.0000

Data Index: 413602 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1886. Min Act: -0.0000

Data Index: 573182 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1318046 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2042. Min Act: -0.0000

Data Index: 876663 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1960. Min Act: -0.0000

Data Index: 564980 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1933. Min Act: -0.0000

Data Index: 836123 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1757. Min Act: -0.0000

Data Index: 640869 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2027. Min Act: -0.0000

Data Index: 242380 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1817. Min Act: 0.0000

Data Index: 262180 (C4 (Web Text))

Max Activating Token Index: 635