Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3405 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.8190. Min Act: -0.0000

Data Index: 1475419 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.8365. Min Act: -0.0000

Data Index: 1581392 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.6277. Min Act: -0.0000

Data Index: 1395545 (Python Code)

Max Activating Token Index: 657

Text #3

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.7026. Min Act: -0.0000

Data Index: 1439850 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.4922. Min Act: -0.0000

Data Index: 1444778 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.3192. Min Act: -0.0000

Data Index: 1562478 (Python Code)

Max Activating Token Index: 748

Text #6

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.0805. Min Act: -0.0000

Data Index: 1427615 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.2495. Min Act: -0.0000

Data Index: 1521152 (Python Code)

Max Activating Token Index: 868

Text #8

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.2593. Min Act: -0.0000

Data Index: 1616947 (Python Code)

Max Activating Token Index: 946

Text #9

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.3532. Min Act: -0.0000

Data Index: 1496239 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.5175. Min Act: -0.0000

Data Index: 1385685 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.3173. Min Act: -0.0000

Data Index: 1467745 (Python Code)

Max Activating Token Index: 571

Text #12

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.1375. Min Act: -0.0000

Data Index: 1641891 (Python Code)

Max Activating Token Index: 583

Text #13

Max Range: 4.8365. Min Range: -4.8365

Max Act: 3.9800. Min Act: -0.0000

Data Index: 1466158 (Python Code)

Max Activating Token Index: 745

Text #14

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.3131. Min Act: -0.0000

Data Index: 1637119 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.3151. Min Act: -0.0000

Data Index: 1580353 (Python Code)

Max Activating Token Index: 334

Text #16

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.2939. Min Act: -0.0000

Data Index: 1624674 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.1040. Min Act: -0.0000

Data Index: 1370658 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.4205. Min Act: -0.0000

Data Index: 1653343 (Python Code)

Max Activating Token Index: 937

Text #19

Max Range: 4.8365. Min Range: -4.8365

Max Act: 4.0739. Min Act: -0.0000

Data Index: 1557361 (Python Code)

Max Activating Token Index: 889