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

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

Neuron 1662 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7528. Min Range: -3.7528

Max Act: 3.7528. Min Act: -0.0000

Data Index: 163862 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 3.7528. Min Range: -3.7528

Max Act: 3.2876. Min Act: -0.0000

Data Index: 2998 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.8952. Min Act: -0.0000

Data Index: 1178903 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.8495. Min Act: -0.0000

Data Index: 116280 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.6170. Min Act: -0.0000

Data Index: 1418251 (Python Code)

Max Activating Token Index: 934

Text #5

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.4682. Min Act: -0.0000

Data Index: 1606942 (Python Code)

Max Activating Token Index: 871

Text #6

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.3435. Min Act: -0.0000

Data Index: 1414848 (Python Code)

Max Activating Token Index: 596

Text #7

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.1346. Min Act: -0.0000

Data Index: 1522116 (Python Code)

Max Activating Token Index: 344

Text #8

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.2529. Min Act: -0.0000

Data Index: 1602980 (Python Code)

Max Activating Token Index: 307

Text #9

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.2420. Min Act: -0.0000

Data Index: 1428741 (Python Code)

Max Activating Token Index: 861

Text #10

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.2535. Min Act: -0.0001

Data Index: 1446477 (Python Code)

Max Activating Token Index: 932

Text #11

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.2163. Min Act: -0.0000

Data Index: 1464267 (Python Code)

Max Activating Token Index: 769

Text #12

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.2857. Min Act: -0.0000

Data Index: 1429417 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.2613. Min Act: -0.0000

Data Index: 1361863 (Python Code)

Max Activating Token Index: 693

Text #14

Max Range: 3.7528. Min Range: -3.7528

Max Act: 1.9707. Min Act: -0.0000

Data Index: 1542829 (Python Code)

Max Activating Token Index: 632

Text #15

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.5991. Min Act: -0.0000

Data Index: 1565390 (Python Code)

Max Activating Token Index: 760

Text #16

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.1208. Min Act: -0.0000

Data Index: 1637359 (Python Code)

Max Activating Token Index: 762

Text #17

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.2239. Min Act: -0.0000

Data Index: 1426788 (Python Code)

Max Activating Token Index: 634

Text #18

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.3108. Min Act: -0.0000

Data Index: 1642910 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 3.7528. Min Range: -3.7528

Max Act: 2.1915. Min Act: -0.0000

Data Index: 1442978 (Python Code)

Max Activating Token Index: 474