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

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

Neuron 948 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.4123. Min Act: -0.0000

Data Index: 1551632 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.6075. Min Act: -0.0000

Data Index: 1473815 (Python Code)

Max Activating Token Index: 369

Text #2

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.4414. Min Act: -0.0000

Data Index: 1485789 (Python Code)

Max Activating Token Index: 90

Text #3

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.3109. Min Act: -0.0000

Data Index: 1366142 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.4672. Min Act: -0.0000

Data Index: 1516580 (Python Code)

Max Activating Token Index: 417

Text #5

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.5552. Min Act: -0.0000

Data Index: 1401319 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.2704. Min Act: -0.0000

Data Index: 1551748 (Python Code)

Max Activating Token Index: 300

Text #7

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.1582. Min Act: -0.0000

Data Index: 1428363 (Python Code)

Max Activating Token Index: 438

Text #8

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.0578. Min Act: -0.0000

Data Index: 1573036 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.0942. Min Act: -0.0000

Data Index: 1651649 (Python Code)

Max Activating Token Index: 683

Text #10

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.6472. Min Act: -0.0001

Data Index: 1574386 (Python Code)

Max Activating Token Index: 907

Text #11

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.1810. Min Act: -0.0000

Data Index: 1575861 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.8841. Min Act: -0.0000

Data Index: 1419349 (Python Code)

Max Activating Token Index: 566

Text #13

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.0173. Min Act: -0.0000

Data Index: 1603181 (Python Code)

Max Activating Token Index: 231

Text #14

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.7278. Min Act: -0.0000

Data Index: 1391168 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.0634. Min Act: -0.0000

Data Index: 1502488 (Python Code)

Max Activating Token Index: 236

Text #16

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.8385. Min Act: -0.0000

Data Index: 1528299 (Python Code)

Max Activating Token Index: 544

Text #17

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.7939. Min Act: -0.0000

Data Index: 1540549 (Python Code)

Max Activating Token Index: 881

Text #18

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.0167. Min Act: -0.0000

Data Index: 1442298 (Python Code)

Max Activating Token Index: 379

Text #19

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.8290. Min Act: -0.0000

Data Index: 1488384 (Python Code)

Max Activating Token Index: 320