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

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

Neuron 1770 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: 2.9881. Min Range: -2.9881

Max Act: 2.8727. Min Act: -0.0000

Data Index: 523431 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.9881. Min Act: -0.0000

Data Index: 550582 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.9780. Min Act: -0.0000

Data Index: 604211 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.6546. Min Act: -0.0000

Data Index: 1198342 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.9629. Min Act: -0.0000

Data Index: 817837 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.7397. Min Act: -0.0000

Data Index: 705706 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.7480. Min Act: -0.0000

Data Index: 1501961 (Python Code)

Max Activating Token Index: 180

Text #7

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.4519. Min Act: -0.0000

Data Index: 696098 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.4518. Min Act: -0.0000

Data Index: 283904 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.6809. Min Act: -0.0000

Data Index: 1296705 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.4552. Min Act: -0.0000

Data Index: 563958 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.5455. Min Act: -0.0000

Data Index: 499450 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.4065. Min Act: -0.0000

Data Index: 1165400 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.5013. Min Act: -0.0000

Data Index: 35088 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.4569. Min Act: -0.0000

Data Index: 943783 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.4328. Min Act: -0.0000

Data Index: 1488538 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.5927. Min Act: -0.0000

Data Index: 38332 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.2681. Min Act: -0.0000

Data Index: 97053 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.3446. Min Act: -0.0000

Data Index: 1515597 (Python Code)

Max Activating Token Index: 269

Text #19

Max Range: 2.9881. Min Range: -2.9881

Max Act: 2.2397. Min Act: -0.0000

Data Index: 800753 (C4 (Web Text))

Max Activating Token Index: 758