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

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

Neuron 2894 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.9268. Min Act: -0.0000

Data Index: 148382 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.7854. Min Act: -0.0000

Data Index: 78138 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.8524. Min Act: -0.0000

Data Index: 1009249 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.7278. Min Act: -0.0000

Data Index: 670877 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.6837. Min Act: -0.0000

Data Index: 743929 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5986. Min Act: -0.0000

Data Index: 346709 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.7773. Min Act: -0.0000

Data Index: 199880 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.6717. Min Act: -0.0000

Data Index: 258208 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.6883. Min Act: -0.0000

Data Index: 451752 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5931. Min Act: -0.0000

Data Index: 899386 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5722. Min Act: -0.0000

Data Index: 62063 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5685. Min Act: -0.0000

Data Index: 598000 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5531. Min Act: -0.0000

Data Index: 706655 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.4394. Min Act: -0.0000

Data Index: 1069239 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5204. Min Act: -0.0000

Data Index: 317545 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.4414. Min Act: -0.0000

Data Index: 386643 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.6063. Min Act: -0.0000

Data Index: 1303566 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5118. Min Act: -0.0000

Data Index: 573580 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5065. Min Act: -0.0000

Data Index: 886592 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5030. Min Act: -0.0000

Data Index: 676544 (C4 (Web Text))

Max Activating Token Index: 557