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

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

Neuron 3280 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7688. Min Act: -0.0000

Data Index: 509074 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6811. Min Act: -0.0000

Data Index: 880888 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6315. Min Act: -0.0000

Data Index: 388222 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1152264 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1183410 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1019394 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1271483 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5896. Min Act: -0.0000

Data Index: 733876 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6089. Min Act: -0.0000

Data Index: 842078 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6252. Min Act: -0.0000

Data Index: 120375 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5199. Min Act: -0.0000

Data Index: 734641 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5374. Min Act: -0.0000

Data Index: 816429 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5592. Min Act: -0.0000

Data Index: 531140 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5028. Min Act: -0.0000

Data Index: 7272 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5224. Min Act: -0.0000

Data Index: 443578 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.4626. Min Act: -0.0000

Data Index: 98306 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5097. Min Act: -0.0000

Data Index: 218600 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.4963. Min Act: -0.0000

Data Index: 529696 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.4366. Min Act: -0.0000

Data Index: 729424 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5085. Min Act: -0.0000

Data Index: 226505 (C4 (Web Text))

Max Activating Token Index: 803