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

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

Neuron 3559 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: 0.2885. Min Range: -0.2885

Max Act: 0.2830. Min Act: -0.0000

Data Index: 44183 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1128045 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2638. Min Act: -0.0000

Data Index: 587581 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1324307 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2649. Min Act: -0.0000

Data Index: 610112 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2632. Min Act: -0.0000

Data Index: 82565 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2707. Min Act: -0.0000

Data Index: 602586 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1099940 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2643. Min Act: -0.0000

Data Index: 662836 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2510. Min Act: -0.0000

Data Index: 804820 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1181245 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1426690 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2248. Min Act: -0.0000

Data Index: 398603 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2201. Min Act: -0.0000

Data Index: 498824 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2015. Min Act: -0.0000

Data Index: 545430 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1314119 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1402876 (Python Code)

Max Activating Token Index: 138

Text #17

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1537654 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1364065 (Python Code)

Max Activating Token Index: 178

Text #19

Max Range: 0.2885. Min Range: -0.2885

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1539475 (Python Code)

Max Activating Token Index: 197