Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 454 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.8468. Min Act: -0.1700

Data Index: 1486293 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.7217. Min Act: -0.1700

Data Index: 1374249 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.6591. Min Act: -0.1700

Data Index: 1626023 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.6278. Min Act: -0.1700

Data Index: 1462693 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.6278. Min Act: -0.1700

Data Index: 1618961 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5964. Min Act: -0.1700

Data Index: 1498611 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5964. Min Act: -0.1700

Data Index: 1583487 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5964. Min Act: -0.1700

Data Index: 1634338 (Python Code)

Max Activating Token Index: 928

Text #8

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5964. Min Act: -0.1700

Data Index: 1520761 (Python Code)

Max Activating Token Index: 133

Text #9

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.6278. Min Act: -0.1700

Data Index: 1594966 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5964. Min Act: -0.1700

Data Index: 1435249 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5964. Min Act: -0.1700

Data Index: 1431254 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5651. Min Act: -0.1700

Data Index: 1593027 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5964. Min Act: -0.1700

Data Index: 1592869 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5651. Min Act: -0.1700

Data Index: 1652857 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5338. Min Act: -0.1700

Data Index: 1583333 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5338. Min Act: -0.1700

Data Index: 1499594 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5338. Min Act: -0.1700

Data Index: 1399795 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5338. Min Act: -0.1700

Data Index: 1565455 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 3.8468. Min Range: -3.8468

Max Act: 3.5651. Min Act: -0.1700

Data Index: 1639799 (Python Code)

Max Activating Token Index: 12