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

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

Neuron 2592 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: 0.9668. Min Range: -0.9668

Max Act: 0.9534. Min Act: -0.0000

Data Index: 659974 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.9668. Min Act: -0.0000

Data Index: 656281 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.9449. Min Act: -0.0000

Data Index: 898537 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8775. Min Act: -0.0000

Data Index: 408859 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8789. Min Act: 0.0002

Data Index: 514131 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8493. Min Act: -0.0000

Data Index: 506630 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8637. Min Act: 0.0000

Data Index: 994410 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8467. Min Act: -0.0000

Data Index: 8454 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1258196 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7838. Min Act: -0.0000

Data Index: 189781 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7859. Min Act: 0.0000

Data Index: 391565 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7279. Min Act: -0.0000

Data Index: 111115 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1347501 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7055. Min Act: -0.0000

Data Index: 223799 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7040. Min Act: -0.0000

Data Index: 44811 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1523717 (Python Code)

Max Activating Token Index: 765

Text #16

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7246. Min Act: -0.0000

Data Index: 840356 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1171881 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.6772. Min Act: 0.0000

Data Index: 1105958 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.6770. Min Act: 0.0000

Data Index: 350674 (C4 (Web Text))

Max Activating Token Index: 622