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

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

Neuron 2842 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: 0.3185. Min Range: -0.3185

Max Act: 0.3185. Min Act: -0.0002

Data Index: 1090907 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3181. Min Act: -0.0002

Data Index: 419586 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3170. Min Act: -0.0002

Data Index: 865519 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3045. Min Act: -0.0002

Data Index: 384998 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3095. Min Act: -0.0002

Data Index: 551360 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3030. Min Act: -0.0002

Data Index: 279987 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3066. Min Act: -0.0002

Data Index: 621545 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3037. Min Act: -0.0002

Data Index: 927610 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3021. Min Act: -0.0002

Data Index: 498126 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2936. Min Act: -0.0002

Data Index: 640784 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3008. Min Act: -0.0002

Data Index: 1243108 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2958. Min Act: -0.0002

Data Index: 642107 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2979. Min Act: -0.0002

Data Index: 1196954 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2921. Min Act: -0.0002

Data Index: 353582 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2989. Min Act: -0.0002

Data Index: 128257 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2890. Min Act: -0.0002

Data Index: 1012010 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2908. Min Act: -0.0002

Data Index: 911747 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2946. Min Act: -0.0002

Data Index: 1300914 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2903. Min Act: -0.0002

Data Index: 349105 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2979. Min Act: -0.0002

Data Index: 836429 (C4 (Web Text))

Max Activating Token Index: 82