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

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

Neuron 3917 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1823. Min Act: -0.0000

Data Index: 555405 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1023138 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1250735 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1656. Min Act: -0.0000

Data Index: 739536 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1340802 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1619. Min Act: -0.0000

Data Index: 167340 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1315361 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1755. Min Act: -0.0000

Data Index: 734713 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1148624 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1205176 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1543. Min Act: -0.0000

Data Index: 487916 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1650. Min Act: -0.0000

Data Index: 333465 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1581. Min Act: -0.0000

Data Index: 49161 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1563. Min Act: -0.0000

Data Index: 142409 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1097127 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1427. Min Act: -0.0000

Data Index: 877919 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1469. Min Act: -0.0000

Data Index: 848677 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1203042 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1297614 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1428. Min Act: -0.0000

Data Index: 364469 (C4 (Web Text))

Max Activating Token Index: 299