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

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

Neuron 1168 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: 3.2662. Min Range: -3.2662

Max Act: 3.2662. Min Act: -0.1700

Data Index: 748249 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1718. Min Act: -0.1700

Data Index: 1581248 (Python Code)

Max Activating Token Index: 1022

Text #2

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.2348. Min Act: -0.1700

Data Index: 1524281 (Python Code)

Max Activating Token Index: 966

Text #3

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.2033. Min Act: -0.1700

Data Index: 237041 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1718. Min Act: -0.1700

Data Index: 705198 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1718. Min Act: -0.1700

Data Index: 1040431 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1404. Min Act: -0.1700

Data Index: 1583124 (Python Code)

Max Activating Token Index: 940

Text #7

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1404. Min Act: -0.1700

Data Index: 1506848 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1718. Min Act: -0.1700

Data Index: 466546 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1404. Min Act: -0.1700

Data Index: 785065 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1088. Min Act: -0.1700

Data Index: 4924 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0457. Min Act: -0.1700

Data Index: 1414023 (Python Code)

Max Activating Token Index: 832

Text #12

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1088. Min Act: -0.1700

Data Index: 1537246 (Python Code)

Max Activating Token Index: 909

Text #13

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0931. Min Act: -0.1700

Data Index: 1495813 (Python Code)

Max Activating Token Index: 839

Text #14

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1404. Min Act: -0.1700

Data Index: 1530329 (Python Code)

Max Activating Token Index: 736

Text #15

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0773. Min Act: -0.1700

Data Index: 1226427 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1088. Min Act: -0.1700

Data Index: 672596 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1088. Min Act: -0.1700

Data Index: 550256 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1088. Min Act: -0.1700

Data Index: 254319 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1088. Min Act: -0.1700

Data Index: 1123985 (C4 (Web Text))

Max Activating Token Index: 760