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

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

Neuron 4336 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: 1.9693. Min Range: -1.9693

Max Act: 1.9693. Min Act: -0.0000

Data Index: 450799 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.7989. Min Act: -0.0000

Data Index: 315227 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.7908. Min Act: -0.0000

Data Index: 1005165 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.6369. Min Act: -0.0000

Data Index: 237874 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.6244. Min Act: -0.0000

Data Index: 1300167 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.5044. Min Act: -0.0000

Data Index: 1318149 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.5453. Min Act: -0.0000

Data Index: 469271 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.3350. Min Act: -0.0000

Data Index: 646303 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.3832. Min Act: -0.0000

Data Index: 393967 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.4002. Min Act: -0.0000

Data Index: 786991 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.3819. Min Act: -0.0000

Data Index: 10344 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.4505. Min Act: -0.0000

Data Index: 1321746 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.3354. Min Act: -0.0000

Data Index: 139535 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.2312. Min Act: -0.0000

Data Index: 194009 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1217319 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.2896. Min Act: -0.0000

Data Index: 85823 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.1987. Min Act: -0.0000

Data Index: 95325 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.2690. Min Act: -0.0000

Data Index: 736610 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.2655. Min Act: -0.0000

Data Index: 510344 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.2597. Min Act: -0.0000

Data Index: 418553 (C4 (Web Text))

Max Activating Token Index: 935