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

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

Neuron 3160 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0942. Min Act: -0.0003

Data Index: 1315933 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1169171 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0937. Min Act: -0.0003

Data Index: 307845 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0844. Min Act: -0.0003

Data Index: 446958 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0908. Min Act: -0.0003

Data Index: 913537 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0815. Min Act: -0.0002

Data Index: 769483 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0835. Min Act: -0.0002

Data Index: 594161 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0824. Min Act: -0.0003

Data Index: 1359081 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0805. Min Act: -0.0003

Data Index: 1517555 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0810. Min Act: -0.0003

Data Index: 1593951 (Python Code)

Max Activating Token Index: 358

Text #10

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0829. Min Act: -0.0003

Data Index: 1432634 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0775. Min Act: -0.0002

Data Index: 932393 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1609972 (Python Code)

Max Activating Token Index: 624

Text #13

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1183807 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0758. Min Act: -0.0003

Data Index: 200763 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1439070 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1147939 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1374142 (Python Code)

Max Activating Token Index: 431

Text #18

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0758. Min Act: -0.0002

Data Index: 330263 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1451143 (Python Code)

Max Activating Token Index: 80