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

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

Neuron 1001 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1312. Min Act: -0.0000

Data Index: 210589 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1225547 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1187. Min Act: -0.0000

Data Index: 81611 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1194. Min Act: -0.0000

Data Index: 929876 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1187. Min Act: -0.0000

Data Index: 307182 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1073. Min Act: -0.0000

Data Index: 660826 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1112. Min Act: -0.0000

Data Index: 75383 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1072. Min Act: -0.0000

Data Index: 335037 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1102. Min Act: -0.0000

Data Index: 173144 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1031. Min Act: -0.0000

Data Index: 131147 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1072. Min Act: -0.0000

Data Index: 119099 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1013545 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1078. Min Act: -0.0000

Data Index: 283410 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1050. Min Act: -0.0000

Data Index: 385578 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1068. Min Act: -0.0000

Data Index: 629853 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1123. Min Act: -0.0000

Data Index: 892787 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1357442 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1038. Min Act: -0.0000

Data Index: 793989 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1276331 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1001. Min Act: -0.0000

Data Index: 44484 (C4 (Web Text))

Max Activating Token Index: 625