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

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

Neuron 1399 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.5056. Min Act: -0.0001

Data Index: 1617797 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.4089. Min Act: -0.0001

Data Index: 1546881 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3642. Min Act: -0.0001

Data Index: 1654912 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1602615 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3240. Min Act: -0.0001

Data Index: 1560798 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1523347 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2818. Min Act: -0.0001

Data Index: 1578727 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2917. Min Act: -0.0001

Data Index: 1503999 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2954. Min Act: -0.0001

Data Index: 1500455 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2859. Min Act: -0.0001

Data Index: 1476549 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2673. Min Act: -0.0001

Data Index: 1557328 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2677. Min Act: -0.0001

Data Index: 1624381 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2666. Min Act: -0.0001

Data Index: 1535458 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2761. Min Act: -0.0001

Data Index: 1412837 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2560. Min Act: -0.0001

Data Index: 1649373 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1363624 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2610. Min Act: -0.0001

Data Index: 1443614 (Python Code)

Max Activating Token Index: 17

Text #17

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2563. Min Act: -0.0001

Data Index: 1579303 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2542. Min Act: -0.0001

Data Index: 1467705 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.2567. Min Act: -0.0001

Data Index: 1646592 (Python Code)

Max Activating Token Index: 12