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

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

Neuron 464 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.7898. Min Act: -0.1700

Data Index: 769062 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.6648. Min Act: -0.1700

Data Index: 931479 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.4773. Min Act: -0.1700

Data Index: 191951 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.4773. Min Act: -0.1700

Data Index: 444098 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.2585. Min Act: -0.1700

Data Index: 1352122 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1960. Min Act: -0.1700

Data Index: 52409 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1960. Min Act: -0.1700

Data Index: 705990 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1335. Min Act: -0.1700

Data Index: 587392 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1335. Min Act: -0.1700

Data Index: 664759 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1648. Min Act: -0.1700

Data Index: 1238696 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1648. Min Act: -0.1700

Data Index: 1027994 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1648. Min Act: -0.1700

Data Index: 1236849 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1648. Min Act: -0.1700

Data Index: 1121472 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1023. Min Act: -0.1700

Data Index: 515587 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1023. Min Act: -0.1700

Data Index: 278707 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1335. Min Act: -0.1700

Data Index: 1202677 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.0710. Min Act: -0.1700

Data Index: 1018932 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1335. Min Act: -0.1700

Data Index: 326526 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.0710. Min Act: -0.1700

Data Index: 767328 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 5.7898. Min Range: -5.7898

Max Act: 5.1023. Min Act: -0.1700

Data Index: 581843 (C4 (Web Text))

Max Activating Token Index: 202