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

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

Neuron 6042 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: 1.4631. Min Range: -1.4631

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1388638 (Python Code)

Max Activating Token Index: 1021

Text #1

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.4631. Min Act: -0.0000

Data Index: 1399432 (Python Code)

Max Activating Token Index: 791

Text #2

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1633963 (Python Code)

Max Activating Token Index: 842

Text #3

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.3094. Min Act: -0.0000

Data Index: 1640627 (Python Code)

Max Activating Token Index: 236

Text #4

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2465. Min Act: -0.0000

Data Index: 1472868 (Python Code)

Max Activating Token Index: 985

Text #5

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1552954 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1513789 (Python Code)

Max Activating Token Index: 388

Text #7

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2335. Min Act: -0.0000

Data Index: 1500669 (Python Code)

Max Activating Token Index: 290

Text #8

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1603. Min Act: -0.0000

Data Index: 1526270 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1372147 (Python Code)

Max Activating Token Index: 180

Text #10

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2309. Min Act: -0.0000

Data Index: 1412605 (Python Code)

Max Activating Token Index: 657

Text #11

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2675. Min Act: -0.0000

Data Index: 1441885 (Python Code)

Max Activating Token Index: 389

Text #12

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2115. Min Act: -0.0000

Data Index: 1513570 (Python Code)

Max Activating Token Index: 512

Text #13

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2107. Min Act: -0.0000

Data Index: 1590161 (Python Code)

Max Activating Token Index: 559

Text #14

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1590813 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1486055 (Python Code)

Max Activating Token Index: 844

Text #16

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2007. Min Act: -0.0000

Data Index: 1570400 (Python Code)

Max Activating Token Index: 132

Text #17

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1489. Min Act: -0.0000

Data Index: 1636638 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1581855 (Python Code)

Max Activating Token Index: 833

Text #19

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1617261 (Python Code)

Max Activating Token Index: 987