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

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

Neuron 1800 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0986. Min Act: -0.0002

Data Index: 398189 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0852. Min Act: -0.0002

Data Index: 194263 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1227993 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1062. Min Act: -0.0002

Data Index: 328303 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1305865 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0796. Min Act: -0.0002

Data Index: 67586 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0752. Min Act: -0.0002

Data Index: 524558 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0771. Min Act: -0.0002

Data Index: 487509 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0809. Min Act: -0.0002

Data Index: 325338 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0673. Min Act: -0.0002

Data Index: 994081 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0715. Min Act: -0.0002

Data Index: 317108 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1286386 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0692. Min Act: -0.0002

Data Index: 467284 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0711. Min Act: -0.0002

Data Index: 560947 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1253191 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0632. Min Act: -0.0002

Data Index: 348835 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1289984 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1030635 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0653. Min Act: -0.0002

Data Index: 984240 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0643. Min Act: -0.0002

Data Index: 853573 (C4 (Web Text))

Max Activating Token Index: 290