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

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

Neuron 1115 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: 5.0125. Min Range: -5.0125

Max Act: 5.0125. Min Act: -0.1700

Data Index: 190543 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 5.0125. Min Range: -5.0125

Max Act: 5.0125. Min Act: -0.1700

Data Index: 337787 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.9187. Min Act: -0.1700

Data Index: 367244 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.9500. Min Act: -0.1700

Data Index: 74331 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.9187. Min Act: -0.1700

Data Index: 743218 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.9187. Min Act: -0.1700

Data Index: 85849 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.9187. Min Act: -0.1700

Data Index: 818688 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.9187. Min Act: -0.1700

Data Index: 288411 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.8875. Min Act: -0.1700

Data Index: 172442 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.9500. Min Act: -0.1700

Data Index: 149203 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.9187. Min Act: -0.1700

Data Index: 847317 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.8875. Min Act: -0.1700

Data Index: 1017244 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.8562. Min Act: -0.1700

Data Index: 887294 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.8562. Min Act: -0.1700

Data Index: 1115640 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.8875. Min Act: -0.1700

Data Index: 1151757 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.9187. Min Act: -0.1700

Data Index: 560680 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.8562. Min Act: -0.1700

Data Index: 588055 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.8875. Min Act: -0.1700

Data Index: 454577 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.8562. Min Act: -0.1700

Data Index: 778333 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 5.0125. Min Range: -5.0125

Max Act: 4.9187. Min Act: -0.1700

Data Index: 34376 (C4 (Web Text))

Max Activating Token Index: 974