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

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

Neuron 3760 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.3651. Min Act: -0.0001

Data Index: 1508952 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.6494. Min Act: -0.0001

Data Index: 1380282 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.3921. Min Act: -0.0001

Data Index: 1540416 (Python Code)

Max Activating Token Index: 375

Text #3

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.2209. Min Act: -0.0001

Data Index: 1403239 (Python Code)

Max Activating Token Index: 672

Text #4

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.5799. Min Act: -0.0001

Data Index: 439611 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.5416. Min Act: -0.0001

Data Index: 1621980 (Python Code)

Max Activating Token Index: 539

Text #6

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.2572. Min Act: -0.0001

Data Index: 1641466 (Python Code)

Max Activating Token Index: 536

Text #7

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.3768. Min Act: -0.0001

Data Index: 1620684 (Python Code)

Max Activating Token Index: 469

Text #8

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.8501. Min Act: -0.0001

Data Index: 1447533 (Python Code)

Max Activating Token Index: 221

Text #9

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.2073. Min Act: -0.0001

Data Index: 1642966 (Python Code)

Max Activating Token Index: 300

Text #10

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.0358. Min Act: -0.0001

Data Index: 1411098 (Python Code)

Max Activating Token Index: 524

Text #11

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.8728. Min Act: -0.0001

Data Index: 1477616 (Python Code)

Max Activating Token Index: 695

Text #12

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.1587. Min Act: -0.0001

Data Index: 1535587 (Python Code)

Max Activating Token Index: 321

Text #13

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.7588. Min Act: -0.0001

Data Index: 1651149 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.2026. Min Act: -0.0001

Data Index: 1637782 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.0405. Min Act: -0.0001

Data Index: 1586063 (Python Code)

Max Activating Token Index: 575

Text #16

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.6378. Min Act: -0.0001

Data Index: 1421003 (Python Code)

Max Activating Token Index: 528

Text #17

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.7720. Min Act: -0.0001

Data Index: 1421540 (Python Code)

Max Activating Token Index: 500

Text #18

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.0057. Min Act: -0.0001

Data Index: 1561613 (Python Code)

Max Activating Token Index: 818

Text #19

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.8824. Min Act: -0.0001

Data Index: 1370055 (Python Code)

Max Activating Token Index: 817