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

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

Neuron 722 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: 4.8012. Min Range: -4.8012

Max Act: 4.8012. Min Act: -0.1700

Data Index: 476003 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.7699. Min Act: -0.1700

Data Index: 728790 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.7699. Min Act: -0.1700

Data Index: 279196 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.7074. Min Act: -0.1700

Data Index: 668148 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.6605. Min Act: -0.1700

Data Index: 1283800 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.6449. Min Act: -0.1700

Data Index: 495971 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.7543. Min Act: -0.1700

Data Index: 1036000 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.7543. Min Act: -0.1700

Data Index: 902471 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.6762. Min Act: -0.1700

Data Index: 856909 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.7230. Min Act: -0.1700

Data Index: 482842 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.5980. Min Act: -0.1700

Data Index: 1245339 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.6293. Min Act: -0.1700

Data Index: 479062 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.6605. Min Act: -0.1700

Data Index: 736755 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.7230. Min Act: -0.1700

Data Index: 614467 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.6137. Min Act: -0.1700

Data Index: 298065 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.5512. Min Act: -0.1700

Data Index: 937167 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.6293. Min Act: -0.1700

Data Index: 768604 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.6293. Min Act: -0.1700

Data Index: 1019331 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.5512. Min Act: -0.1700

Data Index: 309669 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 4.8012. Min Range: -4.8012

Max Act: 4.5199. Min Act: -0.1700

Data Index: 270756 (C4 (Web Text))

Max Activating Token Index: 497