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

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

Neuron 4129 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: 0.5438. Min Range: -0.5438

Max Act: 0.5438. Min Act: -0.0001

Data Index: 1546953 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5355. Min Act: -0.0001

Data Index: 1653327 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5158. Min Act: -0.0001

Data Index: 1476497 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1546202 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5158. Min Act: -0.0001

Data Index: 1622961 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1552965 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1636080 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5158. Min Act: -0.0001

Data Index: 1470897 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1646262 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1429262 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5090. Min Act: -0.0001

Data Index: 1579574 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1394592 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1603640 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1529007 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4660. Min Act: -0.0001

Data Index: 1644238 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4625. Min Act: -0.0001

Data Index: 1555453 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4742. Min Act: -0.0000

Data Index: 1581273 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4758. Min Act: -0.0001

Data Index: 1633795 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4569. Min Act: -0.0001

Data Index: 1486178 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4849. Min Act: -0.0001

Data Index: 1397101 (Python Code)

Max Activating Token Index: 10