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

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

Neuron 549 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1395768 (Python Code)

Max Activating Token Index: 712

Text #1

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1654125 (Python Code)

Max Activating Token Index: 497

Text #2

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1652340 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2265. Min Act: -0.0001

Data Index: 1604993 (Python Code)

Max Activating Token Index: 867

Text #4

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2335. Min Act: -0.0001

Data Index: 1525281 (Python Code)

Max Activating Token Index: 910

Text #5

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1467587 (Python Code)

Max Activating Token Index: 826

Text #6

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1503208 (Python Code)

Max Activating Token Index: 950

Text #7

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1365280 (Python Code)

Max Activating Token Index: 120

Text #8

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1192572 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1724. Min Act: -0.0000

Data Index: 32261 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1458. Min Act: -0.0000

Data Index: 107360 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1050954 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1252655 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1487. Min Act: -0.0000

Data Index: 903175 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1008474 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1090838 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1419. Min Act: -0.0000

Data Index: 809122 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1641509 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1314211 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1225664 (C4 (Web Text))

Max Activating Token Index: 513