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

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

Neuron 841 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.7615. Min Act: -0.0001

Data Index: 1604720 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6191. Min Act: -0.0001

Data Index: 1626536 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6031. Min Act: -0.0001

Data Index: 1598856 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5717. Min Act: -0.0001

Data Index: 1630559 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5895. Min Act: -0.0001

Data Index: 1517513 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5803. Min Act: -0.0001

Data Index: 1536999 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5620. Min Act: -0.0001

Data Index: 1596500 (Python Code)

Max Activating Token Index: 299

Text #7

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5424. Min Act: -0.0001

Data Index: 1565970 (Python Code)

Max Activating Token Index: 415

Text #8

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5757. Min Act: -0.0001

Data Index: 1500417 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5222. Min Act: -0.0001

Data Index: 1546465 (Python Code)

Max Activating Token Index: 674

Text #10

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5540. Min Act: -0.0001

Data Index: 1506978 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5533. Min Act: -0.0001

Data Index: 1630219 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5332. Min Act: -0.0001

Data Index: 1572405 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5356. Min Act: -0.0001

Data Index: 1592704 (Python Code)

Max Activating Token Index: 871

Text #14

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5088. Min Act: -0.0001

Data Index: 1648837 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5083. Min Act: -0.0001

Data Index: 1469425 (Python Code)

Max Activating Token Index: 194

Text #16

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5260. Min Act: -0.0001

Data Index: 1445032 (Python Code)

Max Activating Token Index: 794

Text #17

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5056. Min Act: -0.0001

Data Index: 1599747 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5380. Min Act: -0.0001

Data Index: 1646073 (Python Code)

Max Activating Token Index: 735

Text #19

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5226. Min Act: -0.0001

Data Index: 1503312 (Python Code)

Max Activating Token Index: 81