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

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

Neuron 3037 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.4382. Min Act: -0.0000

Data Index: 1360579 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.2783. Min Act: -0.0000

Data Index: 1414682 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.4365. Min Act: -0.0000

Data Index: 1418401 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.2797. Min Act: -0.0000

Data Index: 1439811 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.4261. Min Act: -0.0000

Data Index: 1606885 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.4249. Min Act: -0.0000

Data Index: 1564639 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.4168. Min Act: -0.0001

Data Index: 1539824 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.2840. Min Act: -0.0000

Data Index: 1539024 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.4028. Min Act: -0.0000

Data Index: 1516835 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.3297. Min Act: -0.0000

Data Index: 1399219 (Python Code)

Max Activating Token Index: 772

Text #10

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.3360. Min Act: -0.0001

Data Index: 1472653 (Python Code)

Max Activating Token Index: 659

Text #11

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.1775. Min Act: -0.0000

Data Index: 1492230 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.3106. Min Act: -0.0000

Data Index: 1459686 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.3000. Min Act: -0.0000

Data Index: 1515752 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.3057. Min Act: -0.0001

Data Index: 1379952 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.2830. Min Act: -0.0000

Data Index: 1383775 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.2988. Min Act: -0.0000

Data Index: 1611072 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.2988. Min Act: -0.0000

Data Index: 1512397 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.2988. Min Act: -0.0000

Data Index: 1649213 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 3.4382. Min Range: -3.4382

Max Act: 3.1594. Min Act: -0.0000

Data Index: 1562466 (Python Code)

Max Activating Token Index: 6