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

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

Neuron 6125 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: 1.6631. Min Range: -1.6631

Max Act: 1.6631. Min Act: -0.0001

Data Index: 1250526 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.6023. Min Act: -0.0001

Data Index: 344454 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.5870. Min Act: -0.0001

Data Index: 25300 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.4271. Min Act: -0.0001

Data Index: 842020 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.2843. Min Act: -0.0000

Data Index: 132785 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.2179. Min Act: -0.0001

Data Index: 1163418 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.0060. Min Act: -0.0001

Data Index: 425727 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.1659. Min Act: -0.0001

Data Index: 866068 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.1090. Min Act: -0.0001

Data Index: 1143011 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 1.6631. Min Range: -1.6631

Max Act: 0.9863. Min Act: -0.0001

Data Index: 1325057 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 1.6631. Min Range: -1.6631

Max Act: 0.9908. Min Act: -0.0001

Data Index: 269161 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.0633. Min Act: -0.0001

Data Index: 554388 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1062469 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.0370. Min Act: -0.0001

Data Index: 875550 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.0307. Min Act: -0.0001

Data Index: 538673 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 1.6631. Min Range: -1.6631

Max Act: 0.9839. Min Act: -0.0001

Data Index: 1286229 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.6631. Min Range: -1.6631

Max Act: 0.9476. Min Act: -0.0001

Data Index: 225827 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.0343. Min Act: -0.0001

Data Index: 329839 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.6631. Min Range: -1.6631

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1304881 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.6631. Min Range: -1.6631

Max Act: 0.9489. Min Act: -0.0000

Data Index: 473045 (C4 (Web Text))

Max Activating Token Index: 789