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

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

Neuron 4215 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.1325. Min Act: -0.0000

Data Index: 637864 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1528823 (Python Code)

Max Activating Token Index: 531

Text #2

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0313. Min Act: -0.0000

Data Index: 1315591 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.9731. Min Act: -0.0000

Data Index: 74855 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.9839. Min Act: -0.0000

Data Index: 144880 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.9446. Min Act: -0.0000

Data Index: 319801 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1490812 (Python Code)

Max Activating Token Index: 350

Text #7

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.8501. Min Act: -0.0000

Data Index: 1456994 (Python Code)

Max Activating Token Index: 101

Text #8

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1453434 (Python Code)

Max Activating Token Index: 929

Text #9

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.7849. Min Act: -0.0000

Data Index: 290558 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.8061. Min Act: -0.0000

Data Index: 829821 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.7877. Min Act: -0.0000

Data Index: 68957 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1209125 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1381983 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.7701. Min Act: -0.0000

Data Index: 369409 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1078568 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.6534. Min Act: -0.0000

Data Index: 648121 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1350585 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.7608. Min Act: -0.0000

Data Index: 673851 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1114433 (C4 (Web Text))

Max Activating Token Index: 708