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

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

Neuron 4343 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0580. Min Range: -1.0580

Max Act: 1.0580. Min Act: -0.0000

Data Index: 1470281 (Python Code)

Max Activating Token Index: 393

Text #1

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.9683. Min Act: -0.0000

Data Index: 1382534 (Python Code)

Max Activating Token Index: 709

Text #2

Max Range: 1.0580. Min Range: -1.0580

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1500410 (Python Code)

Max Activating Token Index: 1015

Text #3

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1651159 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1509997 (Python Code)

Max Activating Token Index: 750

Text #5

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1395714 (Python Code)

Max Activating Token Index: 419

Text #6

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1549053 (Python Code)

Max Activating Token Index: 161

Text #7

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1360005 (Python Code)

Max Activating Token Index: 288

Text #8

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1642678 (Python Code)

Max Activating Token Index: 228

Text #9

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1545932 (Python Code)

Max Activating Token Index: 855

Text #10

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1371327 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1490254 (Python Code)

Max Activating Token Index: 55

Text #12

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1635535 (Python Code)

Max Activating Token Index: 726

Text #13

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1645851 (Python Code)

Max Activating Token Index: 842

Text #14

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1534437 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1545939 (Python Code)

Max Activating Token Index: 392

Text #16

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1445763 (Python Code)

Max Activating Token Index: 397

Text #17

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1384184 (Python Code)

Max Activating Token Index: 81

Text #18

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1572687 (Python Code)

Max Activating Token Index: 919

Text #19

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1454245 (Python Code)

Max Activating Token Index: 375