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

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

Neuron 2005 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.2383. Min Act: -0.1700

Data Index: 1491084 (Python Code)

Max Activating Token Index: 814

Text #1

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.2383. Min Act: -0.1700

Data Index: 1471874 (Python Code)

Max Activating Token Index: 544

Text #2

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.2069. Min Act: -0.1700

Data Index: 1629771 (Python Code)

Max Activating Token Index: 935

Text #3

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.1597. Min Act: -0.1700

Data Index: 1537047 (Python Code)

Max Activating Token Index: 386

Text #4

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.2069. Min Act: -0.1700

Data Index: 87636 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.2855. Min Act: -0.1700

Data Index: 1655764 (Python Code)

Max Activating Token Index: 854

Text #6

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.1754. Min Act: -0.1700

Data Index: 1586803 (Python Code)

Max Activating Token Index: 420

Text #7

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.2069. Min Act: -0.1700

Data Index: 1251651 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.1754. Min Act: -0.1700

Data Index: 1485473 (Python Code)

Max Activating Token Index: 991

Text #9

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.2383. Min Act: -0.1700

Data Index: 1369863 (Python Code)

Max Activating Token Index: 374

Text #10

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.2069. Min Act: -0.1700

Data Index: 1466594 (Python Code)

Max Activating Token Index: 716

Text #11

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.1754. Min Act: -0.1700

Data Index: 486704 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.1597. Min Act: -0.1700

Data Index: 350679 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.0809. Min Act: -0.1700

Data Index: 1392441 (Python Code)

Max Activating Token Index: 748

Text #14

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.1439. Min Act: -0.1700

Data Index: 1622489 (Python Code)

Max Activating Token Index: 544

Text #15

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.0966. Min Act: -0.1700

Data Index: 1608201 (Python Code)

Max Activating Token Index: 640

Text #16

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.0809. Min Act: -0.1700

Data Index: 652929 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.1282. Min Act: -0.1700

Data Index: 301741 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.1439. Min Act: -0.1700

Data Index: 1535614 (Python Code)

Max Activating Token Index: 422

Text #19

Max Range: 3.2855. Min Range: -3.2855

Max Act: 3.0809. Min Act: -0.1700

Data Index: 1591806 (Python Code)

Max Activating Token Index: 925