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

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

Neuron 4646 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.5755. Min Act: -0.0000

Data Index: 336484 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3957. Min Act: -0.0000

Data Index: 349396 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3155. Min Act: -0.0000

Data Index: 32955 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1217384 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2777. Min Act: -0.0000

Data Index: 619087 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1051064 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1034838 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2730. Min Act: -0.0000

Data Index: 225013 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2649. Min Act: -0.0000

Data Index: 308508 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1290728 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2536. Min Act: -0.0000

Data Index: 942041 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2703. Min Act: -0.0000

Data Index: 169093 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2792. Min Act: -0.0000

Data Index: 148173 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2621. Min Act: -0.0000

Data Index: 471472 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1062688 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2578. Min Act: -0.0000

Data Index: 947149 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1257200 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2715. Min Act: -0.0000

Data Index: 578414 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2600. Min Act: -0.0000

Data Index: 143160 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2414. Min Act: -0.0000

Data Index: 758064 (C4 (Web Text))

Max Activating Token Index: 989