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

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

Neuron 594 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: 3.5803. Min Range: -3.5803

Max Act: 3.5803. Min Act: -0.1700

Data Index: 229802 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.3295. Min Act: -0.1700

Data Index: 1218513 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.2824. Min Act: -0.1700

Data Index: 275365 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.2824. Min Act: -0.1700

Data Index: 1428798 (Python Code)

Max Activating Token Index: 553

Text #4

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.2352. Min Act: -0.1700

Data Index: 1538315 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.2667. Min Act: -0.1700

Data Index: 1526481 (Python Code)

Max Activating Token Index: 840

Text #6

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.2038. Min Act: -0.1700

Data Index: 504031 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1880. Min Act: -0.1700

Data Index: 912736 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1880. Min Act: -0.1700

Data Index: 1614218 (Python Code)

Max Activating Token Index: 47

Text #9

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1880. Min Act: -0.1700

Data Index: 33189 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1723. Min Act: -0.1700

Data Index: 474921 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1565. Min Act: -0.1700

Data Index: 1615698 (Python Code)

Max Activating Token Index: 45

Text #12

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1408. Min Act: -0.1700

Data Index: 1437126 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1723. Min Act: -0.1700

Data Index: 1621871 (Python Code)

Max Activating Token Index: 492

Text #14

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1250. Min Act: -0.1700

Data Index: 1419089 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1250. Min Act: -0.1700

Data Index: 1461626 (Python Code)

Max Activating Token Index: 748

Text #16

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1093. Min Act: -0.1700

Data Index: 896030 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1093. Min Act: -0.1700

Data Index: 1640269 (Python Code)

Max Activating Token Index: 54

Text #18

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.1093. Min Act: -0.1700

Data Index: 1541988 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.0935. Min Act: -0.1700

Data Index: 1607260 (Python Code)

Max Activating Token Index: 73