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

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

Neuron 4392 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: 0.2525. Min Range: -0.2525

Max Act: 0.2525. Min Act: -0.0000

Data Index: 557718 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2380. Min Act: -0.0000

Data Index: 60088 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1017727 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1928. Min Act: -0.0000

Data Index: 633176 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1171906 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1736. Min Act: -0.0000

Data Index: 204301 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1479. Min Act: -0.0000

Data Index: 496614 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1046573 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1276221 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1276148 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1246077 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1274. Min Act: -0.0000

Data Index: 107623 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1387. Min Act: -0.0000

Data Index: 856208 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1221. Min Act: -0.0000

Data Index: 378752 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1426983 (Python Code)

Max Activating Token Index: 775

Text #15

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1346. Min Act: -0.0000

Data Index: 834981 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1328. Min Act: -0.0000

Data Index: 482282 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1233. Min Act: -0.0000

Data Index: 986688 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1262756 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1064. Min Act: -0.0000

Data Index: 451813 (C4 (Web Text))

Max Activating Token Index: 969