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

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

Neuron 82 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: 5.4249. Min Range: -5.4249

Max Act: 5.3937. Min Act: -0.1700

Data Index: 1125380 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.3937. Min Act: -0.1700

Data Index: 34238 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.4249. Min Act: -0.1700

Data Index: 323278 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.3312. Min Act: -0.1700

Data Index: 1585370 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.3624. Min Act: -0.1700

Data Index: 739620 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.3312. Min Act: -0.1700

Data Index: 575137 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.3312. Min Act: -0.1700

Data Index: 961928 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.3312. Min Act: -0.1700

Data Index: 1649302 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2687. Min Act: -0.1700

Data Index: 1432150 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2999. Min Act: -0.1700

Data Index: 1517403 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2999. Min Act: -0.1700

Data Index: 1621732 (Python Code)

Max Activating Token Index: 935

Text #11

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2999. Min Act: -0.1700

Data Index: 1624808 (Python Code)

Max Activating Token Index: 507

Text #12

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2999. Min Act: -0.1700

Data Index: 1577926 (Python Code)

Max Activating Token Index: 343

Text #13

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2687. Min Act: -0.1700

Data Index: 1441750 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2687. Min Act: -0.1700

Data Index: 1642775 (Python Code)

Max Activating Token Index: 851

Text #15

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2999. Min Act: -0.1700

Data Index: 1437712 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2687. Min Act: -0.1700

Data Index: 157592 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2687. Min Act: -0.1700

Data Index: 116890 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2999. Min Act: -0.1700

Data Index: 3506 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 5.4249. Min Range: -5.4249

Max Act: 5.2999. Min Act: -0.1700

Data Index: 924594 (C4 (Web Text))

Max Activating Token Index: 105