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

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

Neuron 1560 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: 5.1620. Min Range: -5.1620

Max Act: 5.1620. Min Act: -0.1700

Data Index: 592855 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0682. Min Act: -0.1700

Data Index: 822647 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0057. Min Act: -0.1700

Data Index: 670704 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0526. Min Act: -0.1700

Data Index: 412602 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0057. Min Act: -0.1700

Data Index: 1210210 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0213. Min Act: -0.1700

Data Index: 1220139 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0526. Min Act: -0.1700

Data Index: 595728 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0370. Min Act: -0.1700

Data Index: 993828 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0213. Min Act: -0.1700

Data Index: 905803 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0057. Min Act: -0.1700

Data Index: 896581 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0057. Min Act: -0.1700

Data Index: 148735 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 5.1620. Min Range: -5.1620

Max Act: 4.9901. Min Act: -0.1700

Data Index: 935391 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0213. Min Act: -0.1700

Data Index: 610669 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 5.1620. Min Range: -5.1620

Max Act: 4.9745. Min Act: -0.1700

Data Index: 266741 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0213. Min Act: -0.1700

Data Index: 151384 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0370. Min Act: -0.1700

Data Index: 801411 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0057. Min Act: -0.1700

Data Index: 80602 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 5.1620. Min Range: -5.1620

Max Act: 4.9588. Min Act: -0.1700

Data Index: 951349 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 5.1620. Min Range: -5.1620

Max Act: 5.0057. Min Act: -0.1700

Data Index: 607760 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 5.1620. Min Range: -5.1620

Max Act: 4.9276. Min Act: -0.1700

Data Index: 996363 (C4 (Web Text))

Max Activating Token Index: 631