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

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

Neuron 1639 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1087. Min Range: -2.1087

Max Act: 2.0317. Min Act: -0.0000

Data Index: 435146 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 2.1087. Min Range: -2.1087

Max Act: 2.1087. Min Act: -0.0000

Data Index: 450887 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.7188. Min Act: -0.0000

Data Index: 570894 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.5897. Min Act: -0.0000

Data Index: 366815 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.7744. Min Act: -0.0000

Data Index: 491096 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.7620. Min Act: -0.0000

Data Index: 817595 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.6994. Min Act: -0.0000

Data Index: 776686 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.7081. Min Act: -0.0000

Data Index: 491476 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.5509. Min Act: -0.0000

Data Index: 715764 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.6453. Min Act: -0.0000

Data Index: 1290274 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.5280. Min Act: 0.0001

Data Index: 1053062 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.6139. Min Act: 0.0000

Data Index: 511288 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.6016. Min Act: 0.0000

Data Index: 189437 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.5846. Min Act: -0.0000

Data Index: 1262562 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.4908. Min Act: -0.0000

Data Index: 533225 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.6691. Min Act: -0.0000

Data Index: 991590 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.5687. Min Act: 0.0000

Data Index: 154937 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.4620. Min Act: 0.0000

Data Index: 454223 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.4201. Min Act: -0.0000

Data Index: 1218845 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 2.1087. Min Range: -2.1087

Max Act: 1.6173. Min Act: -0.0000

Data Index: 813675 (C4 (Web Text))

Max Activating Token Index: 73