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

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

Neuron 965 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: 3.3994. Min Range: -3.3994

Max Act: 3.3680. Min Act: -0.1700

Data Index: 1599232 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.3680. Min Act: -0.1700

Data Index: 1555325 (Python Code)

Max Activating Token Index: 496

Text #2

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.3994. Min Act: -0.1700

Data Index: 1611551 (Python Code)

Max Activating Token Index: 416

Text #3

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.3209. Min Act: -0.1700

Data Index: 1485892 (Python Code)

Max Activating Token Index: 88

Text #4

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.3052. Min Act: -0.1700

Data Index: 712018 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2895. Min Act: -0.1700

Data Index: 386402 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2738. Min Act: -0.1700

Data Index: 1408560 (Python Code)

Max Activating Token Index: 188

Text #7

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2738. Min Act: -0.1700

Data Index: 1461501 (Python Code)

Max Activating Token Index: 794

Text #8

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2895. Min Act: -0.1700

Data Index: 1655016 (Python Code)

Max Activating Token Index: 664

Text #9

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2895. Min Act: -0.1700

Data Index: 1504110 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.3052. Min Act: -0.1700

Data Index: 796278 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2581. Min Act: -0.1700

Data Index: 1454350 (Python Code)

Max Activating Token Index: 265

Text #12

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2424. Min Act: -0.1700

Data Index: 1481202 (Python Code)

Max Activating Token Index: 162

Text #13

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2424. Min Act: -0.1700

Data Index: 1534514 (Python Code)

Max Activating Token Index: 472

Text #14

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2581. Min Act: -0.1700

Data Index: 1408412 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2581. Min Act: -0.1700

Data Index: 1442794 (Python Code)

Max Activating Token Index: 236

Text #16

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2581. Min Act: -0.1700

Data Index: 1191497 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2424. Min Act: -0.1700

Data Index: 1381384 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2424. Min Act: -0.1700

Data Index: 1406899 (Python Code)

Max Activating Token Index: 461

Text #19

Max Range: 3.3994. Min Range: -3.3994

Max Act: 3.2424. Min Act: -0.1700

Data Index: 1511235 (Python Code)

Max Activating Token Index: 199