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

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

Neuron 1876 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: 3.7632. Min Range: -3.7632

Max Act: 3.7632. Min Act: -0.1700

Data Index: 1595236 (Python Code)

Max Activating Token Index: 53

Text #1

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6694. Min Act: -0.1700

Data Index: 370 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6694. Min Act: -0.1700

Data Index: 586028 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6850. Min Act: -0.1700

Data Index: 942227 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6537. Min Act: -0.1700

Data Index: 398307 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6381. Min Act: -0.1700

Data Index: 692003 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6537. Min Act: -0.1700

Data Index: 223910 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6224. Min Act: -0.1700

Data Index: 1185454 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6381. Min Act: -0.1700

Data Index: 1211774 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6537. Min Act: -0.1700

Data Index: 188964 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6381. Min Act: -0.1700

Data Index: 1436577 (Python Code)

Max Activating Token Index: 713

Text #11

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6224. Min Act: -0.1700

Data Index: 958437 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6381. Min Act: -0.1700

Data Index: 240864 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6224. Min Act: -0.1700

Data Index: 363736 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6224. Min Act: -0.1700

Data Index: 622988 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6381. Min Act: -0.1700

Data Index: 810021 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6381. Min Act: -0.1700

Data Index: 1130100 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6068. Min Act: -0.1700

Data Index: 381420 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6224. Min Act: -0.1700

Data Index: 665990 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.6068. Min Act: -0.1700

Data Index: 122698 (C4 (Web Text))

Max Activating Token Index: 458