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

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

Neuron 3690 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.2850. Min Act: -0.0001

Data Index: 1445845 (Python Code)

Max Activating Token Index: 327

Text #1

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.1614. Min Act: -0.0001

Data Index: 1518429 (Python Code)

Max Activating Token Index: 574

Text #2

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.2067. Min Act: -0.0001

Data Index: 1649917 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.1412. Min Act: -0.0001

Data Index: 1540941 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9238. Min Act: -0.0001

Data Index: 1469375 (Python Code)

Max Activating Token Index: 475

Text #5

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.0094. Min Act: -0.0001

Data Index: 1632360 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1510327 (Python Code)

Max Activating Token Index: 979

Text #7

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.0612. Min Act: -0.0001

Data Index: 1407736 (Python Code)

Max Activating Token Index: 724

Text #8

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9838. Min Act: -0.0001

Data Index: 1630240 (Python Code)

Max Activating Token Index: 147

Text #9

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9535. Min Act: -0.0001

Data Index: 1580420 (Python Code)

Max Activating Token Index: 260

Text #10

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9431. Min Act: -0.0001

Data Index: 1571575 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.8178. Min Act: -0.0001

Data Index: 1435157 (Python Code)

Max Activating Token Index: 195

Text #12

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.8978. Min Act: -0.0001

Data Index: 1362698 (Python Code)

Max Activating Token Index: 993

Text #13

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9244. Min Act: -0.0001

Data Index: 1584744 (Python Code)

Max Activating Token Index: 544

Text #14

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9422. Min Act: -0.0001

Data Index: 1606265 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.8669. Min Act: -0.0001

Data Index: 1445562 (Python Code)

Max Activating Token Index: 937

Text #16

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.8951. Min Act: -0.0001

Data Index: 1624957 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.8814. Min Act: -0.0001

Data Index: 1447684 (Python Code)

Max Activating Token Index: 456

Text #18

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.8788. Min Act: -0.0001

Data Index: 1606044 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.7749. Min Act: -0.0001

Data Index: 1496857 (Python Code)

Max Activating Token Index: 907