Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1733 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1847. Min Act: -0.0001

Data Index: 914329 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1676. Min Act: -0.0001

Data Index: 929836 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1816. Min Act: -0.0001

Data Index: 1129662 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1653. Min Act: -0.0001

Data Index: 508477 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1316994 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1711. Min Act: -0.0001

Data Index: 657015 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1647. Min Act: -0.0000

Data Index: 227025 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1566. Min Act: -0.0001

Data Index: 309176 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1203210 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1586. Min Act: -0.0001

Data Index: 676545 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1580. Min Act: -0.0001

Data Index: 599125 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1126912 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1560. Min Act: -0.0001

Data Index: 879470 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1546. Min Act: -0.0001

Data Index: 82935 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1352. Min Act: -0.0001

Data Index: 825844 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1528. Min Act: -0.0000

Data Index: 75082 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1514. Min Act: -0.0000

Data Index: 685772 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1458. Min Act: -0.0001

Data Index: 205917 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1489. Min Act: -0.0000

Data Index: 126238 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1072338 (C4 (Web Text))

Max Activating Token Index: 248