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

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

Neuron 3370 in Layer 1

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: 0.2230. Min Range: -0.2230

Max Act: 0.2230. Min Act: -0.0002

Data Index: 1015263 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1938. Min Act: -0.0002

Data Index: 465940 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1865. Min Act: -0.0002

Data Index: 196419 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1791. Min Act: -0.0002

Data Index: 522827 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1824. Min Act: -0.0002

Data Index: 957110 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1746. Min Act: -0.0002

Data Index: 1001487 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1668. Min Act: -0.0002

Data Index: 688901 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1696. Min Act: -0.0003

Data Index: 731919 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1682. Min Act: -0.0002

Data Index: 520723 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1676. Min Act: -0.0002

Data Index: 503050 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1695. Min Act: -0.0002

Data Index: 598141 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1646. Min Act: -0.0003

Data Index: 1297589 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1676. Min Act: -0.0002

Data Index: 189732 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1641. Min Act: -0.0002

Data Index: 78405 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1662. Min Act: -0.0003

Data Index: 840310 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1647. Min Act: -0.0003

Data Index: 375560 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1629. Min Act: -0.0003

Data Index: 787473 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1611. Min Act: -0.0002

Data Index: 1151402 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1656. Min Act: -0.0003

Data Index: 716586 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1616. Min Act: -0.0003

Data Index: 1304993 (C4 (Web Text))

Max Activating Token Index: 671