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

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

Neuron 1246 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: 3.9468. Min Range: -3.9468

Max Act: 3.9468. Min Act: -0.1700

Data Index: 247852 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.9468. Min Act: -0.1700

Data Index: 628692 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.9155. Min Act: -0.1700

Data Index: 827017 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.9155. Min Act: -0.1700

Data Index: 458861 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8530. Min Act: -0.1700

Data Index: 459949 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8843. Min Act: -0.1700

Data Index: 1069241 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8843. Min Act: -0.1700

Data Index: 793162 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.9468. Min Act: -0.1700

Data Index: 1171640 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8843. Min Act: -0.1700

Data Index: 1172813 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8843. Min Act: -0.1700

Data Index: 1188090 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8217. Min Act: -0.1700

Data Index: 1109969 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8530. Min Act: -0.1700

Data Index: 4900 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8530. Min Act: -0.1700

Data Index: 926614 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8217. Min Act: -0.1700

Data Index: 1168192 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8843. Min Act: -0.1700

Data Index: 69227 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8217. Min Act: -0.1700

Data Index: 767538 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8217. Min Act: -0.1700

Data Index: 696338 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8843. Min Act: -0.1700

Data Index: 73408 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8530. Min Act: -0.1700

Data Index: 540546 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 3.9468. Min Range: -3.9468

Max Act: 3.8217. Min Act: -0.1700

Data Index: 464916 (C4 (Web Text))

Max Activating Token Index: 65