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

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

Neuron 1971 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: 3.8311. Min Range: -3.8311

Max Act: 3.8311. Min Act: -0.1700

Data Index: 1295853 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7998. Min Act: -0.1700

Data Index: 606156 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7685. Min Act: -0.1700

Data Index: 1169365 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7373. Min Act: -0.1700

Data Index: 700618 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.6747. Min Act: -0.1700

Data Index: 1344462 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.6590. Min Act: -0.1700

Data Index: 1359425 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.6434. Min Act: -0.1700

Data Index: 604806 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.6434. Min Act: -0.1700

Data Index: 1312996 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.6121. Min Act: -0.1700

Data Index: 1081049 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.6277. Min Act: -0.1700

Data Index: 1201991 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.6434. Min Act: -0.1700

Data Index: 728777 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.5964. Min Act: -0.1700

Data Index: 779609 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.6277. Min Act: -0.1700

Data Index: 302624 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.5807. Min Act: -0.1700

Data Index: 255891 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.5807. Min Act: -0.1700

Data Index: 1301687 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.5807. Min Act: -0.1700

Data Index: 1320313 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.5651. Min Act: -0.1700

Data Index: 858884 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.5651. Min Act: -0.1700

Data Index: 691410 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.5338. Min Act: -0.1700

Data Index: 396400 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.5651. Min Act: -0.1700

Data Index: 1205922 (C4 (Web Text))

Max Activating Token Index: 88