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

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

Neuron 1478 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.6044. Min Act: -0.1700

Data Index: 1036169 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5574. Min Act: -0.1700

Data Index: 1028074 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5574. Min Act: -0.1700

Data Index: 1113713 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5731. Min Act: -0.1700

Data Index: 940347 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5417. Min Act: -0.1700

Data Index: 865722 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5574. Min Act: -0.1700

Data Index: 308874 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5261. Min Act: -0.1700

Data Index: 468533 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5417. Min Act: -0.1700

Data Index: 1222528 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5261. Min Act: -0.1700

Data Index: 1110439 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5104. Min Act: -0.1700

Data Index: 258946 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5261. Min Act: -0.1700

Data Index: 869992 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5104. Min Act: -0.1700

Data Index: 81895 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5104. Min Act: -0.1700

Data Index: 106139 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.5104. Min Act: -0.1700

Data Index: 433693 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.4947. Min Act: -0.1700

Data Index: 554431 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.4947. Min Act: -0.1700

Data Index: 1096072 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.4947. Min Act: -0.1700

Data Index: 1248414 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.4947. Min Act: -0.1700

Data Index: 776816 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.4947. Min Act: -0.1700

Data Index: 1024294 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 3.6044. Min Range: -3.6044

Max Act: 3.4947. Min Act: -0.1700

Data Index: 46454 (C4 (Web Text))

Max Activating Token Index: 432