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

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

Neuron 1440 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: 3.8030. Min Range: -3.8030

Max Act: 3.8030. Min Act: -0.1700

Data Index: 1016187 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.8030. Min Act: -0.1700

Data Index: 1158851 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.7717. Min Act: -0.1700

Data Index: 974323 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.7717. Min Act: -0.1700

Data Index: 285782 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.7404. Min Act: -0.1700

Data Index: 819914 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.6778. Min Act: -0.1700

Data Index: 667906 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.6465. Min Act: -0.1700

Data Index: 334986 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.6152. Min Act: -0.1700

Data Index: 1044966 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.6465. Min Act: -0.1700

Data Index: 776119 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.6152. Min Act: -0.1700

Data Index: 1296350 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.5839. Min Act: -0.1700

Data Index: 821065 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.5839. Min Act: -0.1700

Data Index: 1241416 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.5839. Min Act: -0.1700

Data Index: 1177478 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.5839. Min Act: -0.1700

Data Index: 847485 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.5526. Min Act: -0.1700

Data Index: 1289872 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.5526. Min Act: -0.1700

Data Index: 529479 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.5526. Min Act: -0.1700

Data Index: 868177 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.5526. Min Act: -0.1700

Data Index: 454919 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.4899. Min Act: -0.1700

Data Index: 880271 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.5526. Min Act: -0.1700

Data Index: 995059 (C4 (Web Text))

Max Activating Token Index: 684