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

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

Neuron 4653 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: 0.0637. Min Range: -0.0637

Max Act: 0.0637. Min Act: -0.0002

Data Index: 378789 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1341939 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0584. Min Act: -0.0002

Data Index: 23820 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1629101 (Python Code)

Max Activating Token Index: 26

Text #4

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1485352 (Python Code)

Max Activating Token Index: 77

Text #5

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1565635 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1614258 (Python Code)

Max Activating Token Index: 454

Text #7

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0532. Min Act: -0.0002

Data Index: 729429 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0526. Min Act: -0.0002

Data Index: 918688 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1439978 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0508. Min Act: -0.0002

Data Index: 292652 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1191258 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1499590 (Python Code)

Max Activating Token Index: 114

Text #13

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1372397 (Python Code)

Max Activating Token Index: 133

Text #14

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0481. Min Act: -0.0002

Data Index: 514559 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1488443 (Python Code)

Max Activating Token Index: 1010

Text #16

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0487. Min Act: -0.0002

Data Index: 185576 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0492. Min Act: -0.0002

Data Index: 309160 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0483. Min Act: -0.0002

Data Index: 433281 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1504419 (Python Code)

Max Activating Token Index: 31