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

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

Neuron 4838 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: 1.4001. Min Range: -1.4001

Max Act: 1.4001. Min Act: -0.0000

Data Index: 1433253 (Python Code)

Max Activating Token Index: 419

Text #1

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1612499 (Python Code)

Max Activating Token Index: 402

Text #2

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.0037. Min Act: -0.0000

Data Index: 342234 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.9511. Min Act: -0.0000

Data Index: 1647309 (Python Code)

Max Activating Token Index: 228

Text #4

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.9310. Min Act: -0.0000

Data Index: 1437068 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1654607 (Python Code)

Max Activating Token Index: 718

Text #6

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1562551 (Python Code)

Max Activating Token Index: 421

Text #7

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1547841 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1640500 (Python Code)

Max Activating Token Index: 229

Text #9

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1502220 (Python Code)

Max Activating Token Index: 604

Text #10

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1372939 (Python Code)

Max Activating Token Index: 389

Text #11

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1373127 (Python Code)

Max Activating Token Index: 317

Text #12

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1513917 (Python Code)

Max Activating Token Index: 824

Text #13

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1382288 (Python Code)

Max Activating Token Index: 457

Text #14

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1392171 (Python Code)

Max Activating Token Index: 512

Text #15

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1463012 (Python Code)

Max Activating Token Index: 967

Text #16

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1628999 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1647885 (Python Code)

Max Activating Token Index: 560

Text #18

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1589614 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 1.4001. Min Range: -1.4001

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1441845 (Python Code)

Max Activating Token Index: 327