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

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

Neuron 1904 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.7387. Min Act: -0.1700

Data Index: 999780 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.7074. Min Act: -0.1700

Data Index: 782841 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6448. Min Act: -0.1700

Data Index: 487934 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6761. Min Act: -0.1700

Data Index: 388279 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5822. Min Act: -0.1700

Data Index: 213311 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6135. Min Act: -0.1700

Data Index: 1273518 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5822. Min Act: -0.1700

Data Index: 300962 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5822. Min Act: -0.1700

Data Index: 1022179 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5822. Min Act: -0.1700

Data Index: 725866 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5665. Min Act: -0.1700

Data Index: 192584 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5509. Min Act: -0.1700

Data Index: 320532 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5352. Min Act: -0.1700

Data Index: 162753 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6135. Min Act: -0.1700

Data Index: 1034373 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5039. Min Act: -0.1700

Data Index: 270906 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5665. Min Act: -0.1700

Data Index: 13011 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5352. Min Act: -0.1700

Data Index: 983925 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5509. Min Act: -0.1700

Data Index: 789088 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5352. Min Act: -0.1700

Data Index: 552755 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5039. Min Act: -0.1700

Data Index: 563312 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.4882. Min Act: -0.1700

Data Index: 803259 (C4 (Web Text))

Max Activating Token Index: 276