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

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

Neuron 1974 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: 4.3649. Min Range: -4.3649

Max Act: 4.3649. Min Act: -0.1700

Data Index: 1464283 (Python Code)

Max Activating Token Index: 1003

Text #1

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.3024. Min Act: -0.1700

Data Index: 1417860 (Python Code)

Max Activating Token Index: 1016

Text #2

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.2711. Min Act: -0.1700

Data Index: 1559732 (Python Code)

Max Activating Token Index: 993

Text #3

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.1930. Min Act: -0.1700

Data Index: 1542705 (Python Code)

Max Activating Token Index: 976

Text #4

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.2242. Min Act: -0.1700

Data Index: 1423206 (Python Code)

Max Activating Token Index: 991

Text #5

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.1461. Min Act: -0.1700

Data Index: 1656066 (Python Code)

Max Activating Token Index: 835

Text #6

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.1461. Min Act: -0.1700

Data Index: 1588129 (Python Code)

Max Activating Token Index: 949

Text #7

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.1617. Min Act: -0.1700

Data Index: 1442926 (Python Code)

Max Activating Token Index: 727

Text #8

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.1930. Min Act: -0.1700

Data Index: 1522377 (Python Code)

Max Activating Token Index: 1006

Text #9

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.1148. Min Act: -0.1700

Data Index: 1645415 (Python Code)

Max Activating Token Index: 878

Text #10

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.0836. Min Act: -0.1700

Data Index: 1578508 (Python Code)

Max Activating Token Index: 955

Text #11

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.1148. Min Act: -0.1700

Data Index: 1414657 (Python Code)

Max Activating Token Index: 698

Text #12

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.0211. Min Act: -0.1700

Data Index: 1411391 (Python Code)

Max Activating Token Index: 779

Text #13

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.1305. Min Act: -0.1700

Data Index: 1412199 (Python Code)

Max Activating Token Index: 991

Text #14

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.0211. Min Act: -0.1700

Data Index: 524334 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.0211. Min Act: -0.1700

Data Index: 1446232 (Python Code)

Max Activating Token Index: 553

Text #16

Max Range: 4.3649. Min Range: -4.3649

Max Act: 3.9898. Min Act: -0.1700

Data Index: 1333720 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 4.3649. Min Range: -4.3649

Max Act: 3.9898. Min Act: -0.1700

Data Index: 1396140 (Python Code)

Max Activating Token Index: 1016

Text #18

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.0054. Min Act: -0.1700

Data Index: 1143089 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 4.3649. Min Range: -4.3649

Max Act: 4.0211. Min Act: -0.1700

Data Index: 1592219 (Python Code)

Max Activating Token Index: 623