Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1591 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1336. Min Range: -4.1336

Max Act: 4.1336. Min Act: -0.0000

Data Index: 1515293 (Python Code)

Max Activating Token Index: 202

Text #1

Max Range: 4.1336. Min Range: -4.1336

Max Act: 3.1037. Min Act: -0.0000

Data Index: 1514592 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.9122. Min Act: -0.0000

Data Index: 1613226 (Python Code)

Max Activating Token Index: 913

Text #3

Max Range: 4.1336. Min Range: -4.1336

Max Act: 3.2374. Min Act: -0.0000

Data Index: 1420487 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.8252. Min Act: -0.0000

Data Index: 1593685 (Python Code)

Max Activating Token Index: 407

Text #5

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.5346. Min Act: -0.0000

Data Index: 1544552 (Python Code)

Max Activating Token Index: 961

Text #6

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.6586. Min Act: -0.0000

Data Index: 1431292 (Python Code)

Max Activating Token Index: 207

Text #7

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.6091. Min Act: -0.0000

Data Index: 1410328 (Python Code)

Max Activating Token Index: 404

Text #8

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.6192. Min Act: -0.0000

Data Index: 1489473 (Python Code)

Max Activating Token Index: 977

Text #9

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.5659. Min Act: -0.0000

Data Index: 1546005 (Python Code)

Max Activating Token Index: 402

Text #10

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.4231. Min Act: -0.0000

Data Index: 1454191 (Python Code)

Max Activating Token Index: 997

Text #11

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.3696. Min Act: -0.0000

Data Index: 1431690 (Python Code)

Max Activating Token Index: 742

Text #12

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.4018. Min Act: -0.0000

Data Index: 1370856 (Python Code)

Max Activating Token Index: 988

Text #13

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.4729. Min Act: -0.0000

Data Index: 1585587 (Python Code)

Max Activating Token Index: 691

Text #14

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.3186. Min Act: -0.0000

Data Index: 1365743 (Python Code)

Max Activating Token Index: 854

Text #15

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.3472. Min Act: -0.0000

Data Index: 1617995 (Python Code)

Max Activating Token Index: 441

Text #16

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.4857. Min Act: -0.0000

Data Index: 1514070 (Python Code)

Max Activating Token Index: 732

Text #17

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.4350. Min Act: -0.0000

Data Index: 1363305 (Python Code)

Max Activating Token Index: 845

Text #18

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.4006. Min Act: -0.0000

Data Index: 1413285 (Python Code)

Max Activating Token Index: 846

Text #19

Max Range: 4.1336. Min Range: -4.1336

Max Act: 2.2648. Min Act: -0.0000

Data Index: 1528385 (Python Code)

Max Activating Token Index: 121