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

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

Neuron 4211 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.5561. Min Act: -0.0002

Data Index: 92884 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4963. Min Act: -0.0002

Data Index: 129104 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4256. Min Act: -0.0003

Data Index: 808499 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4421. Min Act: -0.0003

Data Index: 396744 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4124. Min Act: -0.0003

Data Index: 226761 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4146. Min Act: -0.0002

Data Index: 1357611 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4278. Min Act: -0.0002

Data Index: 40016 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.3150. Min Act: -0.0002

Data Index: 46024 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.3330. Min Act: -0.0003

Data Index: 637424 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.3056. Min Act: -0.0003

Data Index: 1147883 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.2989. Min Act: -0.0003

Data Index: 1230874 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.2883. Min Act: -0.0003

Data Index: 728391 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.3032. Min Act: -0.0002

Data Index: 1337473 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.2860. Min Act: -0.0003

Data Index: 970821 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.2970. Min Act: -0.0003

Data Index: 632459 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.2963. Min Act: -0.0003

Data Index: 1285859 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.2970. Min Act: -0.0003

Data Index: 1263633 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.2744. Min Act: -0.0003

Data Index: 558170 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.2705. Min Act: -0.0003

Data Index: 523596 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.2884. Min Act: -0.0002

Data Index: 1242718 (C4 (Web Text))

Max Activating Token Index: 543