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

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

Neuron 1958 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0892. Min Range: -5.0892

Max Act: 5.0892. Min Act: -0.1700

Data Index: 1064957 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 5.0892. Min Range: -5.0892

Max Act: 5.0267. Min Act: -0.1700

Data Index: 1283090 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.9954. Min Act: -0.1700

Data Index: 245758 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.9017. Min Act: -0.1700

Data Index: 766130 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.8704. Min Act: -0.1700

Data Index: 594857 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7767. Min Act: -0.1700

Data Index: 1119771 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.8392. Min Act: -0.1700

Data Index: 479880 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7767. Min Act: -0.1700

Data Index: 1279729 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.8079. Min Act: -0.1700

Data Index: 876077 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7142. Min Act: -0.1700

Data Index: 222329 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7454. Min Act: -0.1700

Data Index: 543246 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7454. Min Act: -0.1700

Data Index: 1116866 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7454. Min Act: -0.1700

Data Index: 343039 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.6829. Min Act: -0.1700

Data Index: 876859 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7454. Min Act: -0.1700

Data Index: 20540 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7454. Min Act: -0.1700

Data Index: 1241647 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7142. Min Act: -0.1700

Data Index: 645115 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7142. Min Act: -0.1700

Data Index: 830149 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.6829. Min Act: -0.1700

Data Index: 167993 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.6517. Min Act: -0.1700

Data Index: 224364 (C4 (Web Text))

Max Activating Token Index: 398