Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1138 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.7262. Min Act: -0.1700

Data Index: 1356040 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.6010. Min Act: -0.1700

Data Index: 1180679 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.5697. Min Act: -0.1700

Data Index: 773497 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.5697. Min Act: -0.1700

Data Index: 885358 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.5071. Min Act: -0.1700

Data Index: 1351316 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.4444. Min Act: -0.1700

Data Index: 1060168 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.4444. Min Act: -0.1700

Data Index: 478347 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.4130. Min Act: -0.1700

Data Index: 129796 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.4130. Min Act: -0.1700

Data Index: 189207 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.3816. Min Act: -0.1700

Data Index: 904450 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.3816. Min Act: -0.1700

Data Index: 960691 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.3816. Min Act: -0.1700

Data Index: 317727 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.3189. Min Act: -0.1700

Data Index: 818873 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.3503. Min Act: -0.1700

Data Index: 514158 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.3503. Min Act: -0.1700

Data Index: 1035139 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.3189. Min Act: -0.1699

Data Index: 1527717 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.2874. Min Act: -0.1700

Data Index: 1228211 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.3189. Min Act: -0.1700

Data Index: 962771 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.3189. Min Act: -0.1700

Data Index: 123446 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 3.7262. Min Range: -3.7262

Max Act: 3.3503. Min Act: -0.1700

Data Index: 1019617 (C4 (Web Text))

Max Activating Token Index: 11