Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1219 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.9139. Min Act: -0.1700

Data Index: 1654713 (Python Code)

Max Activating Token Index: 56

Text #1

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8798. Min Act: -0.1700

Data Index: 1472528 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8628. Min Act: -0.1700

Data Index: 1480232 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8628. Min Act: -0.1700

Data Index: 1407902 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8628. Min Act: -0.1700

Data Index: 1446184 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8628. Min Act: -0.1700

Data Index: 1108731 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8456. Min Act: -0.1700

Data Index: 1551868 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8285. Min Act: -0.1700

Data Index: 1438284 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8285. Min Act: -0.1700

Data Index: 1586005 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8113. Min Act: -0.1700

Data Index: 633827 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8113. Min Act: -0.1700

Data Index: 1419548 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8113. Min Act: -0.1700

Data Index: 1060844 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8113. Min Act: -0.1700

Data Index: 1080855 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.8028. Min Act: -0.1700

Data Index: 1421424 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.7942. Min Act: -0.1700

Data Index: 1507889 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.7856. Min Act: -0.1700

Data Index: 1495750 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.7856. Min Act: -0.1700

Data Index: 1392625 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.7856. Min Act: -0.1700

Data Index: 1468212 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.7856. Min Act: -0.1700

Data Index: 1597926 (Python Code)

Max Activating Token Index: 106

Text #19

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.7769. Min Act: -0.1700

Data Index: 1414403 (Python Code)

Max Activating Token Index: 573