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

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

Neuron 168 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.7374. Min Act: -0.0000

Data Index: 247433 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6784. Min Act: -0.0000

Data Index: 249533 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1045381 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6548. Min Act: -0.0000

Data Index: 643730 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1016089 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.7105. Min Act: -0.0000

Data Index: 181440 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6728. Min Act: -0.0000

Data Index: 449716 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1016436 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5941. Min Act: -0.0000

Data Index: 185581 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5893. Min Act: -0.0000

Data Index: 1006216 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6042. Min Act: -0.0000

Data Index: 555802 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5841. Min Act: -0.0000

Data Index: 87549 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5963. Min Act: -0.0000

Data Index: 84953 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5737. Min Act: -0.0000

Data Index: 381664 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1349476 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5944. Min Act: -0.0000

Data Index: 998385 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1233591 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5830. Min Act: -0.0000

Data Index: 293195 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5748. Min Act: -0.0000

Data Index: 508151 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5535. Min Act: -0.0000

Data Index: 707060 (C4 (Web Text))

Max Activating Token Index: 348