Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3703 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1323. Min Act: -0.0001

Data Index: 917879 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1363. Min Act: -0.0001

Data Index: 1341527 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1368. Min Act: -0.0001

Data Index: 663568 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1241006 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1280660 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1031. Min Act: -0.0001

Data Index: 371632 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1040. Min Act: -0.0001

Data Index: 660266 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1140182 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1274202 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0976. Min Act: -0.0001

Data Index: 178708 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0949. Min Act: -0.0001

Data Index: 940962 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0992. Min Act: -0.0001

Data Index: 900295 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1295150 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1046. Min Act: -0.0001

Data Index: 819880 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0702. Min Act: -0.0001

Data Index: 1220712 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0906. Min Act: -0.0001

Data Index: 468866 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1204160 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0883. Min Act: -0.0001

Data Index: 884773 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1109466 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0942. Min Act: -0.0001

Data Index: 472683 (C4 (Web Text))

Max Activating Token Index: 279