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

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

Neuron 2871 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: 1.5010. Min Range: -1.5010

Max Act: 1.5010. Min Act: -0.0000

Data Index: 246046 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 1.5010. Min Range: -1.5010

Max Act: 1.1030. Min Act: -0.0000

Data Index: 672262 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 1.5010. Min Range: -1.5010

Max Act: 1.1579. Min Act: -0.0000

Data Index: 209558 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.8472. Min Act: -0.0000

Data Index: 870039 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.8088. Min Act: -0.0000

Data Index: 255080 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.8532. Min Act: -0.0000

Data Index: 652242 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.8428. Min Act: -0.0000

Data Index: 939274 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.8871. Min Act: -0.0000

Data Index: 129692 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.8205. Min Act: -0.0000

Data Index: 959494 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1584959 (Python Code)

Max Activating Token Index: 865

Text #10

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7341. Min Act: -0.0000

Data Index: 149959 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1392389 (Python Code)

Max Activating Token Index: 521

Text #12

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1008208 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7722. Min Act: -0.0000

Data Index: 308442 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1542367 (Python Code)

Max Activating Token Index: 673

Text #15

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1534662 (Python Code)

Max Activating Token Index: 503

Text #16

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1412052 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1466791 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1210780 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1463499 (Python Code)

Max Activating Token Index: 906