Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1504 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.2771. Min Act: -0.1700

Data Index: 588580 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.1827. Min Act: -0.1700

Data Index: 150923 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.1512. Min Act: -0.1700

Data Index: 595504 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.1512. Min Act: -0.1700

Data Index: 239666 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.1670. Min Act: -0.1700

Data Index: 954669 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0882. Min Act: -0.1700

Data Index: 1264142 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0882. Min Act: -0.1700

Data Index: 1060869 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.1040. Min Act: -0.1700

Data Index: 126348 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.1197. Min Act: -0.1700

Data Index: 484248 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0724. Min Act: -0.1700

Data Index: 1237850 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0566. Min Act: -0.1700

Data Index: 106356 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0566. Min Act: -0.1700

Data Index: 914796 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0724. Min Act: -0.1700

Data Index: 851715 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0724. Min Act: -0.1700

Data Index: 491556 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0724. Min Act: -0.1700

Data Index: 221246 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0724. Min Act: -0.1700

Data Index: 1193 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0409. Min Act: -0.1700

Data Index: 121687 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0093. Min Act: -0.1700

Data Index: 1106989 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0409. Min Act: -0.1700

Data Index: 479078 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 3.2771. Min Range: -3.2771

Max Act: 3.0251. Min Act: -0.1700

Data Index: 160725 (C4 (Web Text))

Max Activating Token Index: 780