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

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

Neuron 406 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: 5.5387. Min Range: -5.5387

Max Act: 5.5387. Min Act: -0.1700

Data Index: 530185 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.4762. Min Act: -0.1700

Data Index: 1282726 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.3512. Min Act: -0.1700

Data Index: 802898 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.3512. Min Act: -0.1700

Data Index: 113843 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.3199. Min Act: -0.1700

Data Index: 989864 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.3199. Min Act: -0.1700

Data Index: 948916 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2574. Min Act: -0.1700

Data Index: 38654 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2887. Min Act: -0.1700

Data Index: 826231 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2887. Min Act: -0.1700

Data Index: 791384 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2262. Min Act: -0.1700

Data Index: 322236 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2574. Min Act: -0.1700

Data Index: 972286 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2262. Min Act: -0.1700

Data Index: 509274 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2262. Min Act: -0.1700

Data Index: 811675 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2262. Min Act: -0.1700

Data Index: 1181147 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2262. Min Act: -0.1700

Data Index: 311047 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2262. Min Act: -0.1700

Data Index: 1220287 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.1949. Min Act: -0.1700

Data Index: 757404 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2574. Min Act: -0.1700

Data Index: 999193 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.2262. Min Act: -0.1700

Data Index: 1070454 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 5.5387. Min Range: -5.5387

Max Act: 5.1949. Min Act: -0.1700

Data Index: 1135832 (C4 (Web Text))

Max Activating Token Index: 1006