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

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

Neuron 1940 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: 3.7578. Min Range: -3.7578

Max Act: 3.7266. Min Act: -0.1700

Data Index: 539030 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.7266. Min Act: -0.1700

Data Index: 588847 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.7266. Min Act: -0.1700

Data Index: 251248 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.7266. Min Act: -0.1700

Data Index: 966737 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.7266. Min Act: -0.1699

Data Index: 454369 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.7578. Min Act: -0.1699

Data Index: 732111 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.7266. Min Act: -0.1700

Data Index: 9019 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6953. Min Act: -0.1700

Data Index: 823451 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6953. Min Act: -0.1699

Data Index: 1230094 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.7266. Min Act: -0.1700

Data Index: 1157451 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6640. Min Act: -0.1700

Data Index: 1056627 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6953. Min Act: -0.1700

Data Index: 383684 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6953. Min Act: -0.1700

Data Index: 552111 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6640. Min Act: -0.1700

Data Index: 445167 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6640. Min Act: -0.1699

Data Index: 817805 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6640. Min Act: -0.1699

Data Index: 964863 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6640. Min Act: -0.1700

Data Index: 1275795 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6640. Min Act: -0.1700

Data Index: 18874 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6640. Min Act: -0.1700

Data Index: 1319950 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 3.7578. Min Range: -3.7578

Max Act: 3.6327. Min Act: -0.1697

Data Index: 842762 (C4 (Web Text))

Max Activating Token Index: 949