Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1736 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.0880. Min Range: -7.0880

Max Act: 7.0880. Min Act: -0.1700

Data Index: 1401160 (Python Code)

Max Activating Token Index: 848

Text #1

Max Range: 7.0880. Min Range: -7.0880

Max Act: 7.0880. Min Act: -0.1700

Data Index: 1598360 (Python Code)

Max Activating Token Index: 908

Text #2

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.9005. Min Act: -0.1700

Data Index: 1378060 (Python Code)

Max Activating Token Index: 668

Text #3

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.9630. Min Act: -0.1700

Data Index: 1654930 (Python Code)

Max Activating Token Index: 829

Text #4

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.9005. Min Act: -0.1700

Data Index: 1459215 (Python Code)

Max Activating Token Index: 1018

Text #5

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.9005. Min Act: -0.1700

Data Index: 1610452 (Python Code)

Max Activating Token Index: 795

Text #6

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.8380. Min Act: -0.1700

Data Index: 1384553 (Python Code)

Max Activating Token Index: 490

Text #7

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.8380. Min Act: -0.1700

Data Index: 1630448 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.7130. Min Act: -0.1700

Data Index: 1604907 (Python Code)

Max Activating Token Index: 966

Text #9

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.6505. Min Act: -0.1700

Data Index: 1437076 (Python Code)

Max Activating Token Index: 830

Text #10

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.6505. Min Act: -0.1700

Data Index: 1643871 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.5880. Min Act: -0.1700

Data Index: 1596774 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.4630. Min Act: -0.1700

Data Index: 1625435 (Python Code)

Max Activating Token Index: 823

Text #13

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.5255. Min Act: -0.1700

Data Index: 1502827 (Python Code)

Max Activating Token Index: 1006

Text #14

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.5880. Min Act: -0.1700

Data Index: 1469114 (Python Code)

Max Activating Token Index: 953

Text #15

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.4630. Min Act: -0.1700

Data Index: 1544823 (Python Code)

Max Activating Token Index: 877

Text #16

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.5255. Min Act: -0.1700

Data Index: 1463698 (Python Code)

Max Activating Token Index: 955

Text #17

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.5255. Min Act: -0.1700

Data Index: 1490071 (Python Code)

Max Activating Token Index: 998

Text #18

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.4630. Min Act: -0.1700

Data Index: 1602449 (Python Code)

Max Activating Token Index: 968

Text #19

Max Range: 7.0880. Min Range: -7.0880

Max Act: 6.4630. Min Act: -0.1700

Data Index: 1594731 (Python Code)

Max Activating Token Index: 1007