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

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

Neuron 3782 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: 3.3309. Min Range: -3.3309

Max Act: 3.3309. Min Act: -0.0000

Data Index: 1398186 (Python Code)

Max Activating Token Index: 709

Text #1

Max Range: 3.3309. Min Range: -3.3309

Max Act: 2.5664. Min Act: -0.0000

Data Index: 1495457 (Python Code)

Max Activating Token Index: 499

Text #2

Max Range: 3.3309. Min Range: -3.3309

Max Act: 2.2182. Min Act: -0.0000

Data Index: 1439881 (Python Code)

Max Activating Token Index: 566

Text #3

Max Range: 3.3309. Min Range: -3.3309

Max Act: 2.1786. Min Act: -0.0000

Data Index: 1365626 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 3.3309. Min Range: -3.3309

Max Act: 2.1129. Min Act: -0.0000

Data Index: 1424470 (Python Code)

Max Activating Token Index: 398

Text #5

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.7948. Min Act: -0.0000

Data Index: 1614535 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.7956. Min Act: -0.0000

Data Index: 1544684 (Python Code)

Max Activating Token Index: 684

Text #7

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.9532. Min Act: -0.0000

Data Index: 1380205 (Python Code)

Max Activating Token Index: 291

Text #8

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.8598. Min Act: -0.0000

Data Index: 1489466 (Python Code)

Max Activating Token Index: 401

Text #9

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.8432. Min Act: -0.0000

Data Index: 1640545 (Python Code)

Max Activating Token Index: 585

Text #10

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.8302. Min Act: -0.0000

Data Index: 1392227 (Python Code)

Max Activating Token Index: 175

Text #11

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.6107. Min Act: -0.0000

Data Index: 1574067 (Python Code)

Max Activating Token Index: 871

Text #12

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.7248. Min Act: -0.0000

Data Index: 1441291 (Python Code)

Max Activating Token Index: 398

Text #13

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.6754. Min Act: -0.0000

Data Index: 1444604 (Python Code)

Max Activating Token Index: 956

Text #14

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.7648. Min Act: -0.0000

Data Index: 1566517 (Python Code)

Max Activating Token Index: 522

Text #15

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.7528. Min Act: -0.0000

Data Index: 1510198 (Python Code)

Max Activating Token Index: 607

Text #16

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.6530. Min Act: -0.0000

Data Index: 1491668 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.6300. Min Act: -0.0000

Data Index: 1487440 (Python Code)

Max Activating Token Index: 393

Text #18

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.6668. Min Act: -0.0000

Data Index: 1615405 (Python Code)

Max Activating Token Index: 571

Text #19

Max Range: 3.3309. Min Range: -3.3309

Max Act: 1.6126. Min Act: -0.0000

Data Index: 469634 (C4 (Web Text))

Max Activating Token Index: 224