Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3945 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.2988. Min Act: -0.0001

Data Index: 1643000 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.2486. Min Act: -0.0001

Data Index: 1430524 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.2486. Min Act: -0.0001

Data Index: 1365940 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.2486. Min Act: -0.0001

Data Index: 1504416 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.2486. Min Act: -0.0001

Data Index: 1381212 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.2486. Min Act: -0.0001

Data Index: 1542191 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.2486. Min Act: -0.0001

Data Index: 1369640 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.2303. Min Act: -0.0001

Data Index: 1444430 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.1877. Min Act: -0.0001

Data Index: 1365102 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.1877. Min Act: -0.0002

Data Index: 1643452 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.1700. Min Act: -0.0001

Data Index: 1618148 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.1700. Min Act: -0.0001

Data Index: 1623973 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.1700. Min Act: -0.0001

Data Index: 1574807 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.1700. Min Act: -0.0001

Data Index: 1553857 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.1700. Min Act: -0.0001

Data Index: 1644867 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.1700. Min Act: -0.0001

Data Index: 1539843 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.2352. Min Act: -0.0001

Data Index: 1393448 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.1961. Min Act: -0.0001

Data Index: 1428993 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.1961. Min Act: -0.0001

Data Index: 1639279 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.1961. Min Act: -0.0001

Data Index: 1443410 (Python Code)

Max Activating Token Index: 12