Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1683 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.9852. Min Act: -0.1700

Data Index: 980718 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.9343. Min Act: -0.1700

Data Index: 1656248 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.9343. Min Act: -0.1700

Data Index: 17700 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.9173. Min Act: -0.1700

Data Index: 1460476 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.9343. Min Act: -0.1700

Data Index: 1027549 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.9343. Min Act: -0.1700

Data Index: 280698 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.9003. Min Act: -0.1700

Data Index: 336740 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.9003. Min Act: -0.1700

Data Index: 1462861 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8833. Min Act: -0.1700

Data Index: 668148 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8833. Min Act: -0.1700

Data Index: 128302 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8662. Min Act: -0.1700

Data Index: 1263194 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8662. Min Act: -0.1700

Data Index: 775626 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8662. Min Act: -0.1700

Data Index: 25509 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8491. Min Act: -0.1700

Data Index: 910269 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8491. Min Act: -0.1700

Data Index: 1481919 (Python Code)

Max Activating Token Index: 39

Text #15

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8491. Min Act: -0.1700

Data Index: 1461257 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8491. Min Act: -0.1700

Data Index: 1573903 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8662. Min Act: -0.1700

Data Index: 968901 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8319. Min Act: -0.1700

Data Index: 831451 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.8491. Min Act: -0.1700

Data Index: 1203619 (C4 (Web Text))

Max Activating Token Index: 34