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

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

Neuron 4324 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: 0.4352. Min Range: -0.4352

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1418904 (Python Code)

Max Activating Token Index: 404

Text #1

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1613898 (Python Code)

Max Activating Token Index: 803

Text #2

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1600437 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1395145 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1451627 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1428847 (Python Code)

Max Activating Token Index: 663

Text #6

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1426464 (Python Code)

Max Activating Token Index: 274

Text #7

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1541444 (Python Code)

Max Activating Token Index: 453

Text #8

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1376426 (Python Code)

Max Activating Token Index: 692

Text #9

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1445952 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1569801 (Python Code)

Max Activating Token Index: 194

Text #11

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1488036 (Python Code)

Max Activating Token Index: 882

Text #12

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1596437 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1557086 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1641182 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1465174 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1503091 (Python Code)

Max Activating Token Index: 328

Text #17

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1491908 (Python Code)

Max Activating Token Index: 494

Text #18

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1429349 (Python Code)

Max Activating Token Index: 201

Text #19

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1424455 (Python Code)

Max Activating Token Index: 669