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

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

Neuron 4404 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6734. Min Range: -4.6734

Max Act: 4.6734. Min Act: -0.0000

Data Index: 347870 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 4.6734. Min Range: -4.6734

Max Act: 4.5832. Min Act: -0.0000

Data Index: 1121776 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 4.6734. Min Range: -4.6734

Max Act: 4.3914. Min Act: -0.0000

Data Index: 730572 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 4.6734. Min Range: -4.6734

Max Act: 4.2092. Min Act: -0.0000

Data Index: 881768 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 4.6734. Min Range: -4.6734

Max Act: 4.3605. Min Act: -0.0000

Data Index: 438238 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 4.6734. Min Range: -4.6734

Max Act: 4.0695. Min Act: -0.0000

Data Index: 443124 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 4.6734. Min Range: -4.6734

Max Act: 4.2359. Min Act: -0.0000

Data Index: 179608 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 4.6734. Min Range: -4.6734

Max Act: 4.0649. Min Act: -0.0000

Data Index: 166724 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 4.6734. Min Range: -4.6734

Max Act: 4.1576. Min Act: -0.0000

Data Index: 445477 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 4.6734. Min Range: -4.6734

Max Act: 4.0287. Min Act: -0.0000

Data Index: 438906 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 4.6734. Min Range: -4.6734

Max Act: 3.8000. Min Act: -0.0000

Data Index: 215024 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 4.6734. Min Range: -4.6734

Max Act: 3.7939. Min Act: -0.0000

Data Index: 945559 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 4.6734. Min Range: -4.6734

Max Act: 4.1220. Min Act: -0.0000

Data Index: 167280 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 4.6734. Min Range: -4.6734

Max Act: 3.7461. Min Act: -0.0000

Data Index: 160648 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 4.6734. Min Range: -4.6734

Max Act: 3.8842. Min Act: -0.0000

Data Index: 413722 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 4.6734. Min Range: -4.6734

Max Act: 3.8549. Min Act: -0.0000

Data Index: 707184 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 4.6734. Min Range: -4.6734

Max Act: 3.8414. Min Act: -0.0000

Data Index: 538536 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 4.6734. Min Range: -4.6734

Max Act: 3.7706. Min Act: -0.0000

Data Index: 1332572 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 4.6734. Min Range: -4.6734

Max Act: 3.7564. Min Act: -0.0000

Data Index: 107378 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 4.6734. Min Range: -4.6734

Max Act: 3.9003. Min Act: -0.0000

Data Index: 350460 (C4 (Web Text))

Max Activating Token Index: 53