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

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

Neuron 590 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: 1.8281. Min Range: -1.8281

Max Act: 1.6776. Min Act: -0.0000

Data Index: 86613 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.7215. Min Act: -0.0000

Data Index: 309786 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.8281. Min Act: -0.0000

Data Index: 1293398 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.7129. Min Act: -0.0000

Data Index: 1006715 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.4973. Min Act: -0.0000

Data Index: 533116 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.5343. Min Act: -0.0000

Data Index: 315316 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.6250. Min Act: -0.0000

Data Index: 1273944 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.6191. Min Act: -0.0000

Data Index: 715804 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.5783. Min Act: -0.0000

Data Index: 77688 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1198459 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.5685. Min Act: -0.0000

Data Index: 70250 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.4638. Min Act: -0.0000

Data Index: 543636 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.5290. Min Act: -0.0000

Data Index: 139722 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.5951. Min Act: -0.0000

Data Index: 755601 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.5143. Min Act: -0.0000

Data Index: 161973 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.5816. Min Act: -0.0000

Data Index: 919086 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.6106. Min Act: -0.0000

Data Index: 564180 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.4790. Min Act: -0.0000

Data Index: 698981 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1177919 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 1.8281. Min Range: -1.8281

Max Act: 1.4741. Min Act: -0.0000

Data Index: 313786 (C4 (Web Text))

Max Activating Token Index: 652