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

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

Neuron 4239 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.8372. Min Act: -0.0000

Data Index: 1205927 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.7871. Min Act: -0.0000

Data Index: 275985 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.7502. Min Act: -0.0000

Data Index: 435973 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.6002. Min Act: -0.0000

Data Index: 1550167 (Python Code)

Max Activating Token Index: 179

Text #4

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.5799. Min Act: -0.0000

Data Index: 20000 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.3901. Min Act: -0.0000

Data Index: 183196 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1651170 (Python Code)

Max Activating Token Index: 400

Text #7

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.5580. Min Act: -0.0000

Data Index: 536562 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.4824. Min Act: -0.0000

Data Index: 1397107 (Python Code)

Max Activating Token Index: 463

Text #9

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.4362. Min Act: -0.0000

Data Index: 1417922 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.5007. Min Act: -0.0000

Data Index: 175567 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.5195. Min Act: -0.0000

Data Index: 148384 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.3974. Min Act: -0.0000

Data Index: 694977 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.3539. Min Act: -0.0000

Data Index: 305626 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.2780. Min Act: -0.0000

Data Index: 1241582 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.2049. Min Act: -0.0000

Data Index: 661269 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.4515. Min Act: -0.0000

Data Index: 1380193 (Python Code)

Max Activating Token Index: 149

Text #17

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.2996. Min Act: -0.0000

Data Index: 1413260 (Python Code)

Max Activating Token Index: 714

Text #18

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1605321 (Python Code)

Max Activating Token Index: 137

Text #19

Max Range: 1.8372. Min Range: -1.8372

Max Act: 1.4274. Min Act: -0.0000

Data Index: 1632244 (Python Code)

Max Activating Token Index: 872