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

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

Neuron 1113 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: 3.2724. Min Range: -3.2724

Max Act: 3.2724. Min Act: -0.1700

Data Index: 884292 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.2410. Min Act: -0.1700

Data Index: 738008 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.2253. Min Act: -0.1700

Data Index: 687623 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.2096. Min Act: -0.1700

Data Index: 1556377 (Python Code)

Max Activating Token Index: 388

Text #4

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1623. Min Act: -0.1700

Data Index: 78414 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1938. Min Act: -0.1700

Data Index: 297896 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1781. Min Act: -0.1700

Data Index: 33790 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1938. Min Act: -0.1700

Data Index: 1530106 (Python Code)

Max Activating Token Index: 826

Text #8

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1781. Min Act: -0.1700

Data Index: 518099 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1781. Min Act: -0.1700

Data Index: 1036706 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1938. Min Act: -0.1700

Data Index: 1096075 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1781. Min Act: -0.1700

Data Index: 784945 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1623. Min Act: -0.1700

Data Index: 1255087 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1623. Min Act: -0.1700

Data Index: 1105943 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1781. Min Act: -0.1700

Data Index: 485590 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1781. Min Act: -0.1700

Data Index: 684911 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1781. Min Act: -0.1700

Data Index: 983660 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1781. Min Act: -0.1700

Data Index: 478477 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1623. Min Act: -0.1700

Data Index: 11259 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 3.2724. Min Range: -3.2724

Max Act: 3.1623. Min Act: -0.1700

Data Index: 452787 (C4 (Web Text))

Max Activating Token Index: 871