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

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

Neuron 3434 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: 0.9617. Min Range: -0.9617

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1297240 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.8438. Min Act: -0.0000

Data Index: 616581 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1279778 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1038474 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.8178. Min Act: -0.0000

Data Index: 589312 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1043566 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7594. Min Act: -0.0000

Data Index: 663280 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7566. Min Act: -0.0000

Data Index: 705765 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1270120 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7434. Min Act: -0.0000

Data Index: 105103 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7049. Min Act: -0.0000

Data Index: 809770 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1143249 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7052. Min Act: -0.0000

Data Index: 444596 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7254. Min Act: -0.0000

Data Index: 422700 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1356669 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.6774. Min Act: -0.0000

Data Index: 766549 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.6725. Min Act: -0.0000

Data Index: 753600 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.6717. Min Act: -0.0000

Data Index: 451302 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.6351. Min Act: -0.0000

Data Index: 259795 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1316564 (C4 (Web Text))

Max Activating Token Index: 595