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

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

Neuron 2524 in Layer 0

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: 0.7738. Min Range: -0.7738

Max Act: 0.7689. Min Act: -0.0001

Data Index: 1421840 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7738. Min Act: -0.0001

Data Index: 1571545 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7561. Min Act: -0.0001

Data Index: 1495488 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1539455 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1622238 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7324. Min Act: -0.0001

Data Index: 1495279 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1572912 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.4311. Min Act: -0.0001

Data Index: 1497531 (Python Code)

Max Activating Token Index: 821

Text #8

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1610701 (Python Code)

Max Activating Token Index: 893

Text #9

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1484393 (Python Code)

Max Activating Token Index: 706

Text #10

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1566400 (Python Code)

Max Activating Token Index: 821

Text #11

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.3980. Min Act: -0.0001

Data Index: 1480183 (Python Code)

Max Activating Token Index: 724

Text #12

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.3963. Min Act: -0.0001

Data Index: 1640045 (Python Code)

Max Activating Token Index: 876

Text #13

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.3737. Min Act: -0.0001

Data Index: 1467968 (Python Code)

Max Activating Token Index: 748

Text #14

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1604768 (Python Code)

Max Activating Token Index: 647

Text #15

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.3866. Min Act: -0.0001

Data Index: 1462149 (Python Code)

Max Activating Token Index: 669

Text #16

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.3856. Min Act: -0.0001

Data Index: 1407700 (Python Code)

Max Activating Token Index: 577

Text #17

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.3997. Min Act: -0.0001

Data Index: 1377925 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1548759 (Python Code)

Max Activating Token Index: 615

Text #19

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.3932. Min Act: -0.0001

Data Index: 1609377 (Python Code)

Max Activating Token Index: 880