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

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

Neuron 942 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.7372. Min Act: -0.1700

Data Index: 2681 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.7059. Min Act: -0.1700

Data Index: 181739 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.6433. Min Act: -0.1700

Data Index: 554226 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.6433. Min Act: -0.1700

Data Index: 1096103 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.6433. Min Act: -0.1700

Data Index: 524908 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.5807. Min Act: -0.1700

Data Index: 360125 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.5807. Min Act: -0.1700

Data Index: 227981 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.6120. Min Act: -0.1700

Data Index: 888969 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.5807. Min Act: -0.1700

Data Index: 235781 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.5494. Min Act: -0.1700

Data Index: 535436 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.5807. Min Act: -0.1700

Data Index: 405422 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.4867. Min Act: -0.1700

Data Index: 661714 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.5180. Min Act: -0.1700

Data Index: 67350 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.4867. Min Act: -0.1700

Data Index: 790877 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.5180. Min Act: -0.1700

Data Index: 1318161 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.4867. Min Act: -0.1700

Data Index: 790038 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.5180. Min Act: -0.1700

Data Index: 1287275 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.5494. Min Act: -0.1700

Data Index: 509214 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.5180. Min Act: -0.1700

Data Index: 1129278 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 3.7372. Min Range: -3.7372

Max Act: 3.4554. Min Act: -0.1700

Data Index: 59294 (C4 (Web Text))

Max Activating Token Index: 828