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

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

Neuron 1152 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.5790. Min Act: -0.1700

Data Index: 1125091 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.5478. Min Act: -0.1700

Data Index: 712408 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.5165. Min Act: -0.1700

Data Index: 290619 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.4540. Min Act: -0.1700

Data Index: 903163 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.4853. Min Act: -0.1700

Data Index: 1175198 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.4540. Min Act: -0.1700

Data Index: 647871 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.3603. Min Act: -0.1700

Data Index: 155977 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.3603. Min Act: -0.1700

Data Index: 391213 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.2978. Min Act: -0.1700

Data Index: 834337 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.2978. Min Act: -0.1700

Data Index: 1005095 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.2978. Min Act: -0.1700

Data Index: 1313265 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.2978. Min Act: -0.1700

Data Index: 1053398 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.3290. Min Act: -0.1700

Data Index: 259457 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.2978. Min Act: -0.1700

Data Index: 663815 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.3603. Min Act: -0.1700

Data Index: 594660 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.3290. Min Act: -0.1700

Data Index: 1013742 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.2978. Min Act: -0.1700

Data Index: 843158 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.2665. Min Act: -0.1700

Data Index: 594218 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.2040. Min Act: -0.1700

Data Index: 350327 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 5.5790. Min Range: -5.5790

Max Act: 5.2353. Min Act: -0.1700

Data Index: 905733 (C4 (Web Text))

Max Activating Token Index: 880