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

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

Neuron 4338 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.9211. Min Act: -0.0000

Data Index: 1389074 (Python Code)

Max Activating Token Index: 102

Text #1

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.8386. Min Act: -0.0000

Data Index: 1512577 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.8075. Min Act: -0.0000

Data Index: 1614970 (Python Code)

Max Activating Token Index: 65

Text #3

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.9234. Min Act: -0.0000

Data Index: 1390168 (Python Code)

Max Activating Token Index: 411

Text #4

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.9025. Min Act: -0.0000

Data Index: 1405306 (Python Code)

Max Activating Token Index: 151

Text #5

Max Range: 3.0402. Min Range: -3.0402

Max Act: 3.0402. Min Act: -0.0000

Data Index: 1567487 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.6115. Min Act: -0.0000

Data Index: 1387662 (Python Code)

Max Activating Token Index: 901

Text #7

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.6289. Min Act: -0.0000

Data Index: 1512716 (Python Code)

Max Activating Token Index: 829

Text #8

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.6299. Min Act: -0.0000

Data Index: 1549789 (Python Code)

Max Activating Token Index: 355

Text #9

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.7583. Min Act: -0.0000

Data Index: 1541330 (Python Code)

Max Activating Token Index: 139

Text #10

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.7463. Min Act: -0.0000

Data Index: 1398972 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.7176. Min Act: -0.0000

Data Index: 1635973 (Python Code)

Max Activating Token Index: 420

Text #12

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.6889. Min Act: -0.0000

Data Index: 1367307 (Python Code)

Max Activating Token Index: 824

Text #13

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.6806. Min Act: -0.0000

Data Index: 1556336 (Python Code)

Max Activating Token Index: 291

Text #14

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.6920. Min Act: -0.0000

Data Index: 1449015 (Python Code)

Max Activating Token Index: 124

Text #15

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.6502. Min Act: -0.0000

Data Index: 1588989 (Python Code)

Max Activating Token Index: 517

Text #16

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.3818. Min Act: -0.0000

Data Index: 1465037 (Python Code)

Max Activating Token Index: 627

Text #17

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.6273. Min Act: -0.0000

Data Index: 1656456 (Python Code)

Max Activating Token Index: 646

Text #18

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.6096. Min Act: -0.0000

Data Index: 1437816 (Python Code)

Max Activating Token Index: 560

Text #19

Max Range: 3.0402. Min Range: -3.0402

Max Act: 2.6222. Min Act: -0.0000

Data Index: 1406811 (Python Code)

Max Activating Token Index: 84