Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2027 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.7688. Min Act: -0.1700

Data Index: 1134139 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.7375. Min Act: -0.1700

Data Index: 520594 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.7062. Min Act: -0.1700

Data Index: 407730 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.6436. Min Act: -0.1700

Data Index: 681958 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.6123. Min Act: -0.1700

Data Index: 369205 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.5496. Min Act: -0.1700

Data Index: 1127280 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.5340. Min Act: -0.1700

Data Index: 252718 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.5340. Min Act: -0.1700

Data Index: 133514 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.5027. Min Act: -0.1700

Data Index: 1211910 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.5027. Min Act: -0.1700

Data Index: 373399 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.4870. Min Act: -0.1700

Data Index: 165290 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.4713. Min Act: -0.1700

Data Index: 1347022 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.4713. Min Act: -0.1700

Data Index: 1073814 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.4400. Min Act: -0.1700

Data Index: 1059756 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.4400. Min Act: -0.1700

Data Index: 1108341 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.4243. Min Act: -0.1700

Data Index: 534284 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.4400. Min Act: -0.1700

Data Index: 739744 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.4086. Min Act: -0.1700

Data Index: 637302 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.3929. Min Act: -0.1700

Data Index: 656619 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.3772. Min Act: -0.1700

Data Index: 305112 (C4 (Web Text))

Max Activating Token Index: 564