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

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

Neuron 396 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.8441. Min Act: -0.0000

Data Index: 1471672 (Python Code)

Max Activating Token Index: 1018

Text #1

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.8353. Min Act: -0.0000

Data Index: 1629659 (Python Code)

Max Activating Token Index: 971

Text #2

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.6931. Min Act: -0.0000

Data Index: 1453155 (Python Code)

Max Activating Token Index: 893

Text #3

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.7006. Min Act: -0.0000

Data Index: 1504500 (Python Code)

Max Activating Token Index: 689

Text #4

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.5065. Min Act: -0.0000

Data Index: 1483944 (Python Code)

Max Activating Token Index: 1014

Text #5

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.8578. Min Act: -0.0000

Data Index: 1560283 (Python Code)

Max Activating Token Index: 920

Text #6

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.6569. Min Act: -0.0000

Data Index: 1503183 (Python Code)

Max Activating Token Index: 983

Text #7

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.5852. Min Act: -0.0000

Data Index: 1553534 (Python Code)

Max Activating Token Index: 884

Text #8

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.5460. Min Act: -0.0000

Data Index: 1519422 (Python Code)

Max Activating Token Index: 990

Text #9

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.5450. Min Act: -0.0000

Data Index: 1528585 (Python Code)

Max Activating Token Index: 834

Text #10

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.7162. Min Act: -0.0000

Data Index: 1384305 (Python Code)

Max Activating Token Index: 956

Text #11

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.3300. Min Act: -0.0000

Data Index: 1450068 (Python Code)

Max Activating Token Index: 874

Text #12

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.3490. Min Act: -0.0000

Data Index: 1512255 (Python Code)

Max Activating Token Index: 888

Text #13

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.4976. Min Act: -0.0000

Data Index: 1613457 (Python Code)

Max Activating Token Index: 944

Text #14

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.6818. Min Act: -0.0000

Data Index: 1433446 (Python Code)

Max Activating Token Index: 998

Text #15

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.4935. Min Act: -0.0000

Data Index: 1476208 (Python Code)

Max Activating Token Index: 924

Text #16

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.4959. Min Act: -0.0000

Data Index: 1596650 (Python Code)

Max Activating Token Index: 1019

Text #17

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.4858. Min Act: -0.0000

Data Index: 1639659 (Python Code)

Max Activating Token Index: 760

Text #18

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.4696. Min Act: -0.0000

Data Index: 1405768 (Python Code)

Max Activating Token Index: 854

Text #19

Max Range: 4.8578. Min Range: -4.8578

Max Act: 4.0513. Min Act: -0.0000

Data Index: 1457535 (Python Code)

Max Activating Token Index: 786