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

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

Neuron 1392 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.6116. Min Act: -0.1700

Data Index: 334126 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.5646. Min Act: -0.1700

Data Index: 414559 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.5019. Min Act: -0.1700

Data Index: 1468198 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.4706. Min Act: -0.1700

Data Index: 1346250 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.4706. Min Act: -0.1700

Data Index: 145617 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.5019. Min Act: -0.1700

Data Index: 1506511 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.4079. Min Act: -0.1700

Data Index: 2439 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.3608. Min Act: -0.1700

Data Index: 1069533 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.3137. Min Act: -0.1700

Data Index: 1314095 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.3137. Min Act: -0.1700

Data Index: 358544 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.2980. Min Act: -0.1700

Data Index: 469723 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.2980. Min Act: -0.1700

Data Index: 725129 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.3137. Min Act: -0.1700

Data Index: 200607 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.2509. Min Act: -0.1700

Data Index: 1275352 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.2823. Min Act: -0.1700

Data Index: 268543 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.2509. Min Act: -0.1700

Data Index: 1338286 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.2194. Min Act: -0.1700

Data Index: 641450 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.2352. Min Act: -0.1700

Data Index: 300448 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.2509. Min Act: -0.1700

Data Index: 493735 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 3.6116. Min Range: -3.6116

Max Act: 3.2509. Min Act: -0.1700

Data Index: 784837 (C4 (Web Text))

Max Activating Token Index: 194