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

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

Neuron 4030 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: 0.8593. Min Range: -0.8593

Max Act: 0.8593. Min Act: -0.0000

Data Index: 691578 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.8158. Min Act: -0.0000

Data Index: 58517 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6783. Min Act: -0.0000

Data Index: 782704 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6591. Min Act: -0.0000

Data Index: 269600 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6724. Min Act: -0.0000

Data Index: 73461 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6632. Min Act: -0.0000

Data Index: 405660 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6839. Min Act: -0.0000

Data Index: 91397 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1044927 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6523. Min Act: -0.0000

Data Index: 831713 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6461. Min Act: -0.0000

Data Index: 378564 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6198. Min Act: -0.0000

Data Index: 121954 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6217. Min Act: -0.0000

Data Index: 476049 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5930. Min Act: -0.0000

Data Index: 236214 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1093676 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6318. Min Act: -0.0000

Data Index: 678861 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1292954 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5882. Min Act: -0.0000

Data Index: 11915 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5833. Min Act: -0.0000

Data Index: 259982 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5786. Min Act: -0.0000

Data Index: 799621 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1048521 (C4 (Web Text))

Max Activating Token Index: 100