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

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

Neuron 1128 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: 3.7579. Min Range: -3.7579

Max Act: 3.7579. Min Act: -0.1700

Data Index: 377431 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.7110. Min Act: -0.1700

Data Index: 74902 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.7110. Min Act: -0.1700

Data Index: 662054 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.7110. Min Act: -0.1700

Data Index: 232971 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6484. Min Act: -0.1700

Data Index: 1037741 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6484. Min Act: -0.1700

Data Index: 1333184 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6640. Min Act: -0.1700

Data Index: 1198373 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6327. Min Act: -0.1700

Data Index: 101799 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6327. Min Act: -0.1700

Data Index: 801137 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6327. Min Act: -0.1700

Data Index: 499258 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6327. Min Act: -0.1700

Data Index: 948468 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6640. Min Act: -0.1700

Data Index: 678308 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6327. Min Act: -0.1700

Data Index: 1141880 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6484. Min Act: -0.1700

Data Index: 1126265 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6170. Min Act: -0.1700

Data Index: 1158712 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6327. Min Act: -0.1700

Data Index: 1111100 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6327. Min Act: -0.1700

Data Index: 90943 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6327. Min Act: -0.1700

Data Index: 1292798 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6484. Min Act: -0.1700

Data Index: 742064 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 3.7579. Min Range: -3.7579

Max Act: 3.6327. Min Act: -0.1700

Data Index: 755972 (C4 (Web Text))

Max Activating Token Index: 131