Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 564 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.0690. Min Range: -4.0690

Max Act: 4.0690. Min Act: -0.1700

Data Index: 1497341 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8814. Min Act: -0.1700

Data Index: 1443867 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8814. Min Act: -0.1700

Data Index: 1403336 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1379026 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1389955 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1387885 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1408918 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1383540 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1383374 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1379628 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1363689 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1367664 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1377755 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1360043 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1405854 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1375516 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1404027 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1373021 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1399343 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 4.0690. Min Range: -4.0690

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1367975 (Python Code)

Max Activating Token Index: 1