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

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

Neuron 3226 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.8816. Min Act: -0.0000

Data Index: 486571 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.9218. Min Act: -0.0000

Data Index: 277867 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1069661 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.7547. Min Act: -0.0000

Data Index: 336640 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.7548. Min Act: -0.0000

Data Index: 721869 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1131687 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6939. Min Act: -0.0000

Data Index: 364192 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.7181. Min Act: -0.0000

Data Index: 619680 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1338389 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.7090. Min Act: -0.0000

Data Index: 556171 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1193918 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1150640 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1130367 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6284. Min Act: -0.0000

Data Index: 203528 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6267. Min Act: -0.0000

Data Index: 686164 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6003. Min Act: -0.0000

Data Index: 88546 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6397. Min Act: -0.0000

Data Index: 304302 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6182. Min Act: -0.0000

Data Index: 642035 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6350. Min Act: -0.0000

Data Index: 938376 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.9218. Min Range: -0.9218

Max Act: 0.6139. Min Act: -0.0000

Data Index: 477975 (C4 (Web Text))

Max Activating Token Index: 407