Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1601 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9525. Min Act: -0.0001

Data Index: 662418 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9819. Min Act: -0.0001

Data Index: 1376241 (Python Code)

Max Activating Token Index: 684

Text #2

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9054. Min Act: -0.0001

Data Index: 1224906 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8393. Min Act: -0.0001

Data Index: 433246 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8497. Min Act: -0.0001

Data Index: 367945 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8284. Min Act: -0.0001

Data Index: 293424 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8176. Min Act: -0.0001

Data Index: 311722 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7926. Min Act: -0.0001

Data Index: 1413012 (Python Code)

Max Activating Token Index: 605

Text #8

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7795. Min Act: -0.0001

Data Index: 1202075 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7825. Min Act: -0.0001

Data Index: 178013 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7824. Min Act: -0.0001

Data Index: 967185 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7780. Min Act: -0.0001

Data Index: 455874 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7662. Min Act: -0.0001

Data Index: 1565536 (Python Code)

Max Activating Token Index: 612

Text #13

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7850. Min Act: -0.0001

Data Index: 1638584 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7496. Min Act: -0.0001

Data Index: 1481758 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7519. Min Act: -0.0001

Data Index: 1386142 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7731. Min Act: -0.0001

Data Index: 1201947 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7630. Min Act: -0.0001

Data Index: 66043 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7831. Min Act: -0.0001

Data Index: 1006927 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7292. Min Act: -0.0001

Data Index: 1196112 (C4 (Web Text))

Max Activating Token Index: 60