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

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

Neuron 180 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.3958. Min Act: -0.1700

Data Index: 1622844 (Python Code)

Max Activating Token Index: 574

Text #1

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.2388. Min Act: -0.1700

Data Index: 1619957 (Python Code)

Max Activating Token Index: 175

Text #2

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1601. Min Act: -0.1700

Data Index: 1462103 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.2073. Min Act: -0.1700

Data Index: 1620728 (Python Code)

Max Activating Token Index: 930

Text #4

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1286. Min Act: -0.1700

Data Index: 1600784 (Python Code)

Max Activating Token Index: 869

Text #5

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1444. Min Act: -0.1700

Data Index: 1609645 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1444. Min Act: -0.1700

Data Index: 1465562 (Python Code)

Max Activating Token Index: 917

Text #7

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1601. Min Act: -0.1700

Data Index: 1368460 (Python Code)

Max Activating Token Index: 949

Text #8

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.0971. Min Act: -0.1700

Data Index: 750325 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1601. Min Act: -0.1700

Data Index: 1624424 (Python Code)

Max Activating Token Index: 860

Text #10

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1543888 (Python Code)

Max Activating Token Index: 270

Text #11

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1286. Min Act: -0.1700

Data Index: 1656862 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1129. Min Act: -0.1700

Data Index: 201544 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1426428 (Python Code)

Max Activating Token Index: 170

Text #14

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1601361 (Python Code)

Max Activating Token Index: 694

Text #15

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.0971. Min Act: -0.1700

Data Index: 1369103 (Python Code)

Max Activating Token Index: 124

Text #16

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1286. Min Act: -0.1700

Data Index: 1604307 (Python Code)

Max Activating Token Index: 932

Text #17

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1098750 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.0813. Min Act: -0.1700

Data Index: 1513459 (Python Code)

Max Activating Token Index: 64

Text #19

Max Range: 3.3958. Min Range: -3.3958

Max Act: 3.0813. Min Act: -0.1700

Data Index: 1529928 (Python Code)

Max Activating Token Index: 684