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

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

Neuron 2506 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1268880 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1147. Min Act: -0.0001

Data Index: 174958 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1245816 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1096. Min Act: -0.0001

Data Index: 555722 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1023. Min Act: -0.0001

Data Index: 991985 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0984. Min Act: -0.0001

Data Index: 276789 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1022. Min Act: -0.0001

Data Index: 196965 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0965. Min Act: -0.0001

Data Index: 741705 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1185265 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0891. Min Act: -0.0001

Data Index: 640907 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1013. Min Act: -0.0001

Data Index: 198458 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1024. Min Act: -0.0001

Data Index: 345292 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0980. Min Act: -0.0001

Data Index: 188117 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0942. Min Act: -0.0001

Data Index: 5247 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1643041 (Python Code)

Max Activating Token Index: 263

Text #15

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0846. Min Act: -0.0001

Data Index: 77819 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1608657 (Python Code)

Max Activating Token Index: 65

Text #17

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0894. Min Act: -0.0001

Data Index: 674384 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0893. Min Act: -0.0001

Data Index: 287435 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0949. Min Act: -0.0001

Data Index: 751081 (C4 (Web Text))

Max Activating Token Index: 116