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

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

Neuron 1748 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: 971812 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.7387. Min Act: -0.1700

Data Index: 1089992 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6761. Min Act: -0.1700

Data Index: 1336170 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.7074. Min Act: -0.1700

Data Index: 1126380 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.7074. Min Act: -0.1700

Data Index: 365636 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6761. Min Act: -0.1700

Data Index: 484944 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6761. Min Act: -0.1700

Data Index: 987885 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6448. Min Act: -0.1700

Data Index: 696480 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6761. Min Act: -0.1700

Data Index: 1278448 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6448. Min Act: -0.1700

Data Index: 1082614 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6761. Min Act: -0.1700

Data Index: 608364 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6448. Min Act: -0.1700

Data Index: 334001 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6448. Min Act: -0.1700

Data Index: 1198248 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6135. Min Act: -0.1700

Data Index: 341930 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.6135. Min Act: -0.1700

Data Index: 1118939 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5822. Min Act: -0.1700

Data Index: 755304 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5822. Min Act: -0.1700

Data Index: 1084370 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5195. Min Act: -0.1700

Data Index: 791771 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5822. Min Act: -0.1699

Data Index: 512972 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5822. Min Act: -0.1700

Data Index: 1170032 (C4 (Web Text))

Max Activating Token Index: 426