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

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

Neuron 1546 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1478235 (Python Code)

Max Activating Token Index: 794

Text #1

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1601288 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1504169 (Python Code)

Max Activating Token Index: 641

Text #3

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1538340 (Python Code)

Max Activating Token Index: 962

Text #4

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1636410 (Python Code)

Max Activating Token Index: 695

Text #5

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1529495 (Python Code)

Max Activating Token Index: 631

Text #6

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1628137 (Python Code)

Max Activating Token Index: 433

Text #7

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1413439 (Python Code)

Max Activating Token Index: 489

Text #8

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1653134 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1458890 (Python Code)

Max Activating Token Index: 335

Text #10

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1596478 (Python Code)

Max Activating Token Index: 630

Text #11

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1476021 (Python Code)

Max Activating Token Index: 465

Text #12

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1404737 (Python Code)

Max Activating Token Index: 777

Text #13

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1419417 (Python Code)

Max Activating Token Index: 837

Text #14

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1453513 (Python Code)

Max Activating Token Index: 177

Text #15

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1368735 (Python Code)

Max Activating Token Index: 402

Text #16

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1370382 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2178. Min Act: -0.0000

Data Index: 1392285 (Python Code)

Max Activating Token Index: 821

Text #18

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2178. Min Act: -0.0000

Data Index: 1652335 (Python Code)

Max Activating Token Index: 980

Text #19

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1555170 (Python Code)

Max Activating Token Index: 445