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

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

Neuron 5097 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.9436. Min Act: -0.0000

Data Index: 449307 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8108. Min Act: -0.0000

Data Index: 187308 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7203. Min Act: -0.0000

Data Index: 859153 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.6928. Min Act: -0.0000

Data Index: 415854 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.6931. Min Act: -0.0000

Data Index: 422230 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.6107. Min Act: -0.0000

Data Index: 182159 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.6666. Min Act: -0.0000

Data Index: 967121 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.6842. Min Act: -0.0000

Data Index: 796452 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.6515. Min Act: -0.0000

Data Index: 771422 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.5931. Min Act: -0.0000

Data Index: 610197 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.6054. Min Act: -0.0000

Data Index: 221825 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.5808. Min Act: -0.0000

Data Index: 449522 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.5596. Min Act: -0.0000

Data Index: 522896 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.5322. Min Act: -0.0000

Data Index: 387622 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.5408. Min Act: -0.0000

Data Index: 84689 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1012549 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1308218 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.5440. Min Act: -0.0000

Data Index: 881611 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.5261. Min Act: -0.0000

Data Index: 808668 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.5876. Min Act: -0.0000

Data Index: 628791 (C4 (Web Text))

Max Activating Token Index: 849