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

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

Neuron 4500 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0632. Min Act: -0.0001

Data Index: 259470 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0578. Min Act: -0.0001

Data Index: 726442 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0581. Min Act: -0.0001

Data Index: 169095 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0577. Min Act: -0.0001

Data Index: 986137 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0567. Min Act: -0.0001

Data Index: 862631 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0584. Min Act: -0.0001

Data Index: 377959 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0570. Min Act: -0.0001

Data Index: 949940 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0549. Min Act: -0.0001

Data Index: 481652 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1358389 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1038010 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1043960 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0549. Min Act: -0.0001

Data Index: 56315 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0544. Min Act: -0.0001

Data Index: 153937 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0541. Min Act: -0.0001

Data Index: 68721 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0548. Min Act: -0.0001

Data Index: 609279 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1015345 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0550. Min Act: -0.0001

Data Index: 232016 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0535. Min Act: -0.0001

Data Index: 666739 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0541. Min Act: -0.0001

Data Index: 187452 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0543. Min Act: -0.0001

Data Index: 105129 (C4 (Web Text))

Max Activating Token Index: 662