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

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

Neuron 2250 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1070. Min Act: -0.0000

Data Index: 211930 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1112. Min Act: -0.0000

Data Index: 965606 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1151. Min Act: -0.0000

Data Index: 982659 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1159. Min Act: -0.0000

Data Index: 76374 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1070. Min Act: -0.0000

Data Index: 312272 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1050. Min Act: -0.0000

Data Index: 937451 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1013. Min Act: -0.0000

Data Index: 745707 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0970. Min Act: -0.0000

Data Index: 862502 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1039. Min Act: -0.0000

Data Index: 788255 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1188343 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1310279 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0992. Min Act: -0.0000

Data Index: 289372 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0955. Min Act: -0.0000

Data Index: 422383 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1258219 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0942. Min Act: -0.0000

Data Index: 177847 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0970. Min Act: -0.0000

Data Index: 322506 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0975. Min Act: -0.0001

Data Index: 684331 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0896. Min Act: -0.0000

Data Index: 865597 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0934. Min Act: -0.0000

Data Index: 178489 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0920. Min Act: -0.0000

Data Index: 81353 (C4 (Web Text))

Max Activating Token Index: 946