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

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

Neuron 911 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.5267. Min Act: -0.1700

Data Index: 393196 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.4955. Min Act: -0.1700

Data Index: 192282 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.2455. Min Act: -0.1700

Data Index: 1092930 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.2455. Min Act: -0.1700

Data Index: 696933 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.1830. Min Act: -0.1700

Data Index: 950601 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.1517. Min Act: -0.1700

Data Index: 773811 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.0580. Min Act: -0.1700

Data Index: 376226 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.0580. Min Act: -0.1700

Data Index: 695122 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.0267. Min Act: -0.1700

Data Index: 112109 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.0267. Min Act: -0.1700

Data Index: 179807 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.0267. Min Act: -0.1700

Data Index: 1017727 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.0267. Min Act: -0.1700

Data Index: 381229 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.0580. Min Act: -0.1700

Data Index: 880576 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 5.5267. Min Range: -5.5267

Max Act: 4.9642. Min Act: -0.1700

Data Index: 903692 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 5.5267. Min Range: -5.5267

Max Act: 4.9955. Min Act: -0.1700

Data Index: 1163202 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 5.5267. Min Range: -5.5267

Max Act: 5.0580. Min Act: -0.1700

Data Index: 1286712 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 5.5267. Min Range: -5.5267

Max Act: 4.9955. Min Act: -0.1700

Data Index: 367150 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 5.5267. Min Range: -5.5267

Max Act: 4.9642. Min Act: -0.1700

Data Index: 820228 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 5.5267. Min Range: -5.5267

Max Act: 4.9642. Min Act: -0.1700

Data Index: 851016 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 5.5267. Min Range: -5.5267

Max Act: 4.9017. Min Act: -0.1700

Data Index: 1072119 (C4 (Web Text))

Max Activating Token Index: 872