Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1539 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.8057. Min Act: -0.1700

Data Index: 1545010 (Python Code)

Max Activating Token Index: 666

Text #1

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.8098. Min Act: -0.1700

Data Index: 897432 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.7622. Min Act: -0.1700

Data Index: 1452557 (Python Code)

Max Activating Token Index: 465

Text #3

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.7518. Min Act: -0.1700

Data Index: 1632974 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.7346. Min Act: -0.1700

Data Index: 12970 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.7721. Min Act: -0.1700

Data Index: 47926 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6716. Min Act: -0.1700

Data Index: 1640277 (Python Code)

Max Activating Token Index: 357

Text #7

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6720. Min Act: -0.1700

Data Index: 650583 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6920. Min Act: -0.1700

Data Index: 1176339 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6293. Min Act: -0.1700

Data Index: 581159 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6632. Min Act: -0.1700

Data Index: 978605 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6440. Min Act: -0.1700

Data Index: 946446 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6078. Min Act: -0.1700

Data Index: 1192698 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.5959. Min Act: -0.1700

Data Index: 746501 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6068. Min Act: -0.1700

Data Index: 721859 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6291. Min Act: -0.1700

Data Index: 612962 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.5829. Min Act: -0.1700

Data Index: 1480890 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6080. Min Act: -0.1700

Data Index: 1548317 (Python Code)

Max Activating Token Index: 564

Text #18

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6009. Min Act: -0.1700

Data Index: 1435084 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.5905. Min Act: -0.1700

Data Index: 1359259 (C4 (Web Text))

Max Activating Token Index: 20