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

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

Neuron 4700 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0981. Min Range: -1.0981

Max Act: 1.0981. Min Act: -0.0000

Data Index: 356117 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 1.0981. Min Range: -1.0981

Max Act: 1.0276. Min Act: -0.0000

Data Index: 374422 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 1.0981. Min Range: -1.0981

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1243006 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.9669. Min Act: 0.0000

Data Index: 1103501 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1227090 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1099755 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.8529. Min Act: -0.0000

Data Index: 870151 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1252807 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.9091. Min Act: -0.0000

Data Index: 790437 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.8273. Min Act: -0.0000

Data Index: 89651 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1310002 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.8196. Min Act: -0.0000

Data Index: 435671 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.8721. Min Act: -0.0000

Data Index: 209532 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1120201 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.8604. Min Act: -0.0000

Data Index: 81739 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.8322. Min Act: -0.0000

Data Index: 647919 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.8809. Min Act: -0.0000

Data Index: 552165 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.7927. Min Act: -0.0000

Data Index: 709552 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.8149. Min Act: -0.0000

Data Index: 347708 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 1.0981. Min Range: -1.0981

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1217001 (C4 (Web Text))

Max Activating Token Index: 100