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

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

Neuron 313 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1507198 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1466911 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1407725 (Python Code)

Max Activating Token Index: 936

Text #3

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1623226 (Python Code)

Max Activating Token Index: 703

Text #4

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1491875 (Python Code)

Max Activating Token Index: 803

Text #5

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1643673 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1413297 (Python Code)

Max Activating Token Index: 646

Text #7

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1381514 (Python Code)

Max Activating Token Index: 93

Text #8

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1431783 (Python Code)

Max Activating Token Index: 85

Text #9

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1368547 (Python Code)

Max Activating Token Index: 726

Text #10

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1446108 (Python Code)

Max Activating Token Index: 806

Text #11

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1470079 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1507011 (Python Code)

Max Activating Token Index: 985

Text #13

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1583041 (Python Code)

Max Activating Token Index: 986

Text #14

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1482666 (Python Code)

Max Activating Token Index: 936

Text #15

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1501980 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1595101 (Python Code)

Max Activating Token Index: 316

Text #17

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1489751 (Python Code)

Max Activating Token Index: 243

Text #18

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1432948 (Python Code)

Max Activating Token Index: 625

Text #19

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1488827 (Python Code)

Max Activating Token Index: 229