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

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

Neuron 4301 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1967. Min Range: -2.1967

Max Act: 2.0872. Min Act: -0.0000

Data Index: 1548508 (Python Code)

Max Activating Token Index: 608

Text #1

Max Range: 2.1967. Min Range: -2.1967

Max Act: 2.1967. Min Act: -0.0000

Data Index: 1470393 (Python Code)

Max Activating Token Index: 929

Text #2

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.8646. Min Act: -0.0000

Data Index: 1634906 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 2.1967. Min Range: -2.1967

Max Act: 2.0060. Min Act: -0.0000

Data Index: 1377451 (Python Code)

Max Activating Token Index: 748

Text #4

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.7765. Min Act: -0.0000

Data Index: 1635324 (Python Code)

Max Activating Token Index: 809

Text #5

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.8665. Min Act: -0.0000

Data Index: 1408422 (Python Code)

Max Activating Token Index: 957

Text #6

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.8618. Min Act: -0.0000

Data Index: 1367618 (Python Code)

Max Activating Token Index: 540

Text #7

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.8521. Min Act: -0.0000

Data Index: 1529030 (Python Code)

Max Activating Token Index: 648

Text #8

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.8093. Min Act: -0.0000

Data Index: 1620210 (Python Code)

Max Activating Token Index: 973

Text #9

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.8067. Min Act: -0.0000

Data Index: 1421493 (Python Code)

Max Activating Token Index: 592

Text #10

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.8018. Min Act: -0.0000

Data Index: 1641953 (Python Code)

Max Activating Token Index: 791

Text #11

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.7495. Min Act: -0.0000

Data Index: 1376199 (Python Code)

Max Activating Token Index: 84

Text #12

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.7360. Min Act: -0.0000

Data Index: 1510641 (Python Code)

Max Activating Token Index: 80

Text #13

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.8316. Min Act: -0.0000

Data Index: 1589224 (Python Code)

Max Activating Token Index: 740

Text #14

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.7229. Min Act: -0.0000

Data Index: 1587092 (Python Code)

Max Activating Token Index: 360

Text #15

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.8123. Min Act: -0.0000

Data Index: 1451892 (Python Code)

Max Activating Token Index: 424

Text #16

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.9138. Min Act: -0.0000

Data Index: 1483121 (Python Code)

Max Activating Token Index: 968

Text #17

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.5167. Min Act: -0.0000

Data Index: 1587959 (Python Code)

Max Activating Token Index: 999

Text #18

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.7002. Min Act: -0.0000

Data Index: 1479491 (Python Code)

Max Activating Token Index: 42

Text #19

Max Range: 2.1967. Min Range: -2.1967

Max Act: 1.6929. Min Act: -0.0000

Data Index: 1408252 (Python Code)

Max Activating Token Index: 243