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

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

Neuron 1805 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.8190. Min Act: -0.0000

Data Index: 1543787 (Python Code)

Max Activating Token Index: 492

Text #1

Max Range: 2.0937. Min Range: -2.0937

Max Act: 2.0937. Min Act: -0.0000

Data Index: 4364 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.8807. Min Act: -0.0000

Data Index: 436054 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.8378. Min Act: 0.0000

Data Index: 1436363 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.8377. Min Act: 0.0000

Data Index: 1564617 (Python Code)

Max Activating Token Index: 490

Text #5

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.7702. Min Act: 0.0001

Data Index: 1568030 (Python Code)

Max Activating Token Index: 920

Text #6

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.6667. Min Act: -0.0000

Data Index: 1485086 (Python Code)

Max Activating Token Index: 264

Text #7

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.6690. Min Act: -0.0000

Data Index: 1380916 (Python Code)

Max Activating Token Index: 560

Text #8

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.6259. Min Act: 0.0000

Data Index: 1609964 (Python Code)

Max Activating Token Index: 565

Text #9

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.4870. Min Act: -0.0000

Data Index: 1436455 (Python Code)

Max Activating Token Index: 51

Text #10

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.4882. Min Act: -0.0000

Data Index: 1421593 (Python Code)

Max Activating Token Index: 816

Text #11

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.5491. Min Act: -0.0000

Data Index: 1019706 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1494090 (Python Code)

Max Activating Token Index: 397

Text #13

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.4616. Min Act: 0.0000

Data Index: 979926 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.4541. Min Act: -0.0000

Data Index: 1539188 (Python Code)

Max Activating Token Index: 604

Text #15

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.4407. Min Act: -0.0000

Data Index: 1414309 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.4428. Min Act: 0.0000

Data Index: 1475451 (Python Code)

Max Activating Token Index: 515

Text #17

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.4320. Min Act: 0.0001

Data Index: 1396328 (Python Code)

Max Activating Token Index: 906

Text #18

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.3295. Min Act: 0.0000

Data Index: 1644703 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 2.0937. Min Range: -2.0937

Max Act: 1.3749. Min Act: -0.0000

Data Index: 1624738 (Python Code)

Max Activating Token Index: 797