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

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

Neuron 1789 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.8391. Min Act: -0.1700

Data Index: 118351 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.7453. Min Act: -0.1700

Data Index: 116091 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.6828. Min Act: -0.1700

Data Index: 714138 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.5891. Min Act: -0.1700

Data Index: 872937 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.5891. Min Act: -0.1700

Data Index: 543852 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.5578. Min Act: -0.1700

Data Index: 1321337 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.5578. Min Act: -0.1700

Data Index: 100669 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4328. Min Act: -0.1700

Data Index: 537337 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4641. Min Act: -0.1700

Data Index: 961250 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4641. Min Act: -0.1700

Data Index: 273428 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4328. Min Act: -0.1700

Data Index: 1077805 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4328. Min Act: -0.1700

Data Index: 935325 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4953. Min Act: -0.1700

Data Index: 941274 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.3703. Min Act: -0.1700

Data Index: 134784 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4641. Min Act: -0.1700

Data Index: 9352 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.3703. Min Act: -0.1700

Data Index: 750203 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4328. Min Act: -0.1700

Data Index: 1128186 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.3703. Min Act: -0.1700

Data Index: 474619 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4016. Min Act: -0.1700

Data Index: 233872 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4016. Min Act: -0.1700

Data Index: 411397 (C4 (Web Text))

Max Activating Token Index: 171