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

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

Neuron 2249 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: 0.5690. Min Range: -0.5690

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1547779 (Python Code)

Max Activating Token Index: 635

Text #1

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1390434 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1537631 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1480103 (Python Code)

Max Activating Token Index: 585

Text #4

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1429004 (Python Code)

Max Activating Token Index: 304

Text #5

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1601256 (Python Code)

Max Activating Token Index: 959

Text #6

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1577259 (Python Code)

Max Activating Token Index: 215

Text #7

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1391150 (Python Code)

Max Activating Token Index: 351

Text #8

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1634972 (Python Code)

Max Activating Token Index: 493

Text #9

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1550362 (Python Code)

Max Activating Token Index: 105

Text #10

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1591657 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1594202 (Python Code)

Max Activating Token Index: 961

Text #12

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1582118 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1512388 (Python Code)

Max Activating Token Index: 416

Text #14

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1623807 (Python Code)

Max Activating Token Index: 596

Text #15

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1633211 (Python Code)

Max Activating Token Index: 174

Text #16

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4504. Min Act: -0.0000

Data Index: 471967 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1419151 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1577413 (Python Code)

Max Activating Token Index: 560

Text #19

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1404073 (Python Code)

Max Activating Token Index: 935