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

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

Neuron 3407 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.3762. Min Act: -0.0000

Data Index: 144072 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.3196. Min Act: -0.0001

Data Index: 269497 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.3243. Min Act: -0.0001

Data Index: 726499 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1308049 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.3103. Min Act: -0.0000

Data Index: 810263 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.3441. Min Act: -0.0000

Data Index: 677407 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.2946. Min Act: -0.0000

Data Index: 4467 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1476789 (Python Code)

Max Activating Token Index: 189

Text #8

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.2996. Min Act: -0.0001

Data Index: 294345 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1327240 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.2913. Min Act: -0.0000

Data Index: 713941 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.3107. Min Act: -0.0000

Data Index: 238345 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.3040. Min Act: -0.0000

Data Index: 319985 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.2796. Min Act: -0.0000

Data Index: 43196 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1211159 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.3619. Min Act: -0.0000

Data Index: 1097724 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.2829. Min Act: -0.0001

Data Index: 431440 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.2684. Min Act: -0.0000

Data Index: 19010 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.2741. Min Act: -0.0000

Data Index: 640544 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.3762. Min Range: -0.3762

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1099286 (C4 (Web Text))

Max Activating Token Index: 305