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

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

Neuron 5092 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8530. Min Range: -7.8530

Max Act: 7.8530. Min Act: -0.0000

Data Index: 1565375 (Python Code)

Max Activating Token Index: 851

Text #1

Max Range: 7.8530. Min Range: -7.8530

Max Act: 7.2196. Min Act: -0.0000

Data Index: 1463221 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.6694. Min Act: -0.0000

Data Index: 1520753 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 7.8530. Min Range: -7.8530

Max Act: 7.0245. Min Act: -0.0000

Data Index: 1404326 (Python Code)

Max Activating Token Index: 398

Text #4

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.5306. Min Act: -0.0000

Data Index: 1537654 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.8690. Min Act: -0.0000

Data Index: 1477627 (Python Code)

Max Activating Token Index: 999

Text #6

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.2673. Min Act: -0.0000

Data Index: 1546780 (Python Code)

Max Activating Token Index: 804

Text #7

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.7075. Min Act: -0.0000

Data Index: 1431429 (Python Code)

Max Activating Token Index: 31

Text #8

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.4750. Min Act: -0.0000

Data Index: 1613435 (Python Code)

Max Activating Token Index: 438

Text #9

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.3788. Min Act: -0.0000

Data Index: 1468515 (Python Code)

Max Activating Token Index: 500

Text #10

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.5740. Min Act: -0.0000

Data Index: 1480578 (Python Code)

Max Activating Token Index: 462

Text #11

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.7535. Min Act: -0.0000

Data Index: 1597323 (Python Code)

Max Activating Token Index: 735

Text #12

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.5488. Min Act: -0.0000

Data Index: 1436642 (Python Code)

Max Activating Token Index: 638

Text #13

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.4913. Min Act: -0.0000

Data Index: 1607589 (Python Code)

Max Activating Token Index: 811

Text #14

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.6547. Min Act: -0.0000

Data Index: 1412576 (Python Code)

Max Activating Token Index: 944

Text #15

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.2503. Min Act: -0.0000

Data Index: 1596895 (Python Code)

Max Activating Token Index: 994

Text #16

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.4159. Min Act: -0.0000

Data Index: 1366918 (Python Code)

Max Activating Token Index: 716

Text #17

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.2398. Min Act: -0.0000

Data Index: 1555321 (Python Code)

Max Activating Token Index: 335

Text #18

Max Range: 7.8530. Min Range: -7.8530

Max Act: 6.3380. Min Act: -0.0000

Data Index: 1464131 (Python Code)

Max Activating Token Index: 707

Text #19

Max Range: 7.8530. Min Range: -7.8530

Max Act: 5.9510. Min Act: -0.0000

Data Index: 1621163 (Python Code)

Max Activating Token Index: 539