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

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

Neuron 464 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.2097. Min Act: -0.1700

Data Index: 531550 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.1624. Min Act: -0.1700

Data Index: 1084716 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.1467. Min Act: -0.1700

Data Index: 386809 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.0521. Min Act: -0.1700

Data Index: 133960 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.0363. Min Act: -0.1700

Data Index: 1206545 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.0363. Min Act: -0.1700

Data Index: 171012 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.0205. Min Act: -0.1700

Data Index: 752079 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.0205. Min Act: -0.1700

Data Index: 790445 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.0205. Min Act: -0.1700

Data Index: 960186 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.0205. Min Act: -0.1700

Data Index: 1147534 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.0047. Min Act: -0.1700

Data Index: 74304 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.9731. Min Act: -0.1700

Data Index: 1299433 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.9889. Min Act: -0.1700

Data Index: 967915 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.9889. Min Act: -0.1700

Data Index: 991371 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.0047. Min Act: -0.1700

Data Index: 988623 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.9572. Min Act: -0.1700

Data Index: 102385 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.9572. Min Act: -0.1700

Data Index: 829310 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.9731. Min Act: -0.1700

Data Index: 839717 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.9572. Min Act: -0.1700

Data Index: 1056244 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.9572. Min Act: -0.1700

Data Index: 1025817 (C4 (Web Text))

Max Activating Token Index: 656