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

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

Neuron 2763 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: 1.9810. Min Range: -1.9810

Max Act: 1.9810. Min Act: -0.0000

Data Index: 619851 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.8831. Min Act: -0.0000

Data Index: 727101 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.8794. Min Act: -0.0000

Data Index: 90693 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.7491. Min Act: -0.0000

Data Index: 1456240 (Python Code)

Max Activating Token Index: 776

Text #4

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.7230. Min Act: -0.0000

Data Index: 1213729 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.6716. Min Act: -0.0000

Data Index: 825460 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.5650. Min Act: -0.0000

Data Index: 21011 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.4685. Min Act: -0.0000

Data Index: 1518357 (Python Code)

Max Activating Token Index: 991

Text #8

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.4441. Min Act: -0.0000

Data Index: 620123 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.3432. Min Act: 0.0000

Data Index: 1358945 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.3846. Min Act: -0.0000

Data Index: 158558 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1156649 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.2711. Min Act: 0.0000

Data Index: 201211 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.3261. Min Act: -0.0000

Data Index: 350990 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.3986. Min Act: 0.0000

Data Index: 453408 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1216546 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.2975. Min Act: -0.0000

Data Index: 258581 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.2951. Min Act: 0.0000

Data Index: 39622 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.2779. Min Act: 0.0000

Data Index: 1233677 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 1.9810. Min Range: -1.9810

Max Act: 1.2538. Min Act: -0.0000

Data Index: 1052133 (C4 (Web Text))

Max Activating Token Index: 333