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

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

Neuron 5729 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.9201. Min Act: -0.0000

Data Index: 312837 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7686. Min Act: -0.0000

Data Index: 289082 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7883. Min Act: -0.0000

Data Index: 956173 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.8032. Min Act: -0.0000

Data Index: 884026 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1419462 (Python Code)

Max Activating Token Index: 762

Text #5

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7365. Min Act: -0.0000

Data Index: 984209 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1581005 (Python Code)

Max Activating Token Index: 330

Text #7

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1529988 (Python Code)

Max Activating Token Index: 963

Text #8

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7392. Min Act: -0.0000

Data Index: 797462 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6930. Min Act: -0.0000

Data Index: 221845 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6837. Min Act: -0.0000

Data Index: 881374 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7042. Min Act: -0.0000

Data Index: 922376 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1059039 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1223068 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7007. Min Act: -0.0000

Data Index: 62225 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1504026 (Python Code)

Max Activating Token Index: 449

Text #16

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1653132 (Python Code)

Max Activating Token Index: 823

Text #17

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6631. Min Act: -0.0000

Data Index: 453022 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1282580 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6845. Min Act: -0.0000

Data Index: 156374 (C4 (Web Text))

Max Activating Token Index: 900