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

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

Neuron 926 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6987. Min Act: -0.0002

Data Index: 819584 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6796. Min Act: -0.0002

Data Index: 1249416 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6704. Min Act: -0.0002

Data Index: 872505 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6748. Min Act: -0.0002

Data Index: 1114505 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6627. Min Act: -0.0002

Data Index: 1123894 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6530. Min Act: -0.0002

Data Index: 861841 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6473. Min Act: -0.0002

Data Index: 1223080 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6346. Min Act: -0.0002

Data Index: 1300923 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6279. Min Act: -0.0002

Data Index: 618023 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6231. Min Act: -0.0002

Data Index: 644444 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6228. Min Act: -0.0002

Data Index: 54374 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6114. Min Act: -0.0002

Data Index: 1129914 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6200. Min Act: -0.0002

Data Index: 18190 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6130. Min Act: -0.0002

Data Index: 320439 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5984. Min Act: -0.0002

Data Index: 388721 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6017. Min Act: -0.0002

Data Index: 793419 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5995. Min Act: -0.0002

Data Index: 32442 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5954. Min Act: -0.0002

Data Index: 574160 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6042. Min Act: -0.0002

Data Index: 1240362 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5989. Min Act: -0.0002

Data Index: 626008 (C4 (Web Text))

Max Activating Token Index: 38