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

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

Neuron 211 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: 5.2903. Min Range: -5.2903

Max Act: 5.2903. Min Act: -0.1700

Data Index: 1140039 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.1965. Min Act: -0.1697

Data Index: 1148666 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.1965. Min Act: -0.1700

Data Index: 857313 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.1809. Min Act: -0.1698

Data Index: 607950 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.0871. Min Act: -0.1700

Data Index: 639777 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.0715. Min Act: -0.1699

Data Index: 1087508 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.0403. Min Act: -0.1700

Data Index: 919559 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.0559. Min Act: -0.1700

Data Index: 528909 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.0246. Min Act: -0.1700

Data Index: 711180 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.0246. Min Act: -0.1700

Data Index: 794445 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.0715. Min Act: -0.1700

Data Index: 1246371 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.0715. Min Act: -0.1700

Data Index: 986994 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.0246. Min Act: -0.1700

Data Index: 801439 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.0090. Min Act: -0.1700

Data Index: 273411 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 5.2903. Min Range: -5.2903

Max Act: 5.0090. Min Act: -0.1700

Data Index: 561493 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 5.2903. Min Range: -5.2903

Max Act: 4.9934. Min Act: -0.1700

Data Index: 827227 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 5.2903. Min Range: -5.2903

Max Act: 4.9934. Min Act: -0.1700

Data Index: 93953 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 5.2903. Min Range: -5.2903

Max Act: 4.9934. Min Act: -0.1699

Data Index: 757540 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 5.2903. Min Range: -5.2903

Max Act: 4.9934. Min Act: -0.1700

Data Index: 16346 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 5.2903. Min Range: -5.2903

Max Act: 4.9778. Min Act: -0.1700

Data Index: 1041156 (C4 (Web Text))

Max Activating Token Index: 128