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

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

Neuron 5136 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7719. Min Range: -4.7719

Max Act: 4.7719. Min Act: -0.0000

Data Index: 866461 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 4.7719. Min Range: -4.7719

Max Act: 4.2246. Min Act: -0.0000

Data Index: 521738 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 4.7719. Min Range: -4.7719

Max Act: 4.2310. Min Act: -0.0000

Data Index: 115990 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.9339. Min Act: -0.0000

Data Index: 74503 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.6485. Min Act: -0.0000

Data Index: 29592 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.8895. Min Act: -0.0000

Data Index: 958723 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.7962. Min Act: -0.0000

Data Index: 655104 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.7962. Min Act: -0.0000

Data Index: 488224 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.2082. Min Act: -0.0000

Data Index: 598807 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.4549. Min Act: -0.0000

Data Index: 1195203 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.4075. Min Act: -0.0000

Data Index: 1093789 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.3647. Min Act: -0.0000

Data Index: 563931 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.1766. Min Act: -0.0000

Data Index: 1204848 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.3014. Min Act: -0.0000

Data Index: 571944 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.1340. Min Act: -0.0000

Data Index: 765213 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.2739. Min Act: -0.0000

Data Index: 1534668 (Python Code)

Max Activating Token Index: 954

Text #16

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.4097. Min Act: -0.0000

Data Index: 356722 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.4015. Min Act: -0.0000

Data Index: 1178060 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.2397. Min Act: -0.0000

Data Index: 1615924 (Python Code)

Max Activating Token Index: 827

Text #19

Max Range: 4.7719. Min Range: -4.7719

Max Act: 2.9316. Min Act: -0.0000

Data Index: 1289054 (C4 (Web Text))

Max Activating Token Index: 949