Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1174 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1475344 (Python Code)

Max Activating Token Index: 1020

Text #1

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1611394 (Python Code)

Max Activating Token Index: 850

Text #2

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1612307 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1603345 (Python Code)

Max Activating Token Index: 980

Text #4

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1429891 (Python Code)

Max Activating Token Index: 774

Text #5

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1489200 (Python Code)

Max Activating Token Index: 938

Text #6

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1529635 (Python Code)

Max Activating Token Index: 774

Text #7

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1399468 (Python Code)

Max Activating Token Index: 412

Text #8

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1591285 (Python Code)

Max Activating Token Index: 861

Text #9

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4416. Min Act: -0.0001

Data Index: 1581969 (Python Code)

Max Activating Token Index: 713

Text #10

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1456667 (Python Code)

Max Activating Token Index: 984

Text #11

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1466146 (Python Code)

Max Activating Token Index: 666

Text #12

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1631717 (Python Code)

Max Activating Token Index: 878

Text #13

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.3823. Min Act: -0.0000

Data Index: 1579945 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1566416 (Python Code)

Max Activating Token Index: 562

Text #15

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1546420 (Python Code)

Max Activating Token Index: 572

Text #16

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.3525. Min Act: -0.0001

Data Index: 1451325 (Python Code)

Max Activating Token Index: 780

Text #17

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1509511 (Python Code)

Max Activating Token Index: 650

Text #18

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1472329 (Python Code)

Max Activating Token Index: 756

Text #19

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1422355 (Python Code)

Max Activating Token Index: 1012