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

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

Neuron 1145 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.7749. Min Act: -0.1700

Data Index: 1310849 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.8062. Min Act: -0.1630

Data Index: 227833 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.6499. Min Act: -0.1700

Data Index: 567573 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.5874. Min Act: -0.1700

Data Index: 623353 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.5562. Min Act: -0.1700

Data Index: 300642 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.5562. Min Act: -0.1700

Data Index: 758992 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.5249. Min Act: -0.1700

Data Index: 1069739 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.5249. Min Act: -0.1700

Data Index: 1306914 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.5249. Min Act: -0.1170

Data Index: 172042 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.4937. Min Act: -0.1700

Data Index: 1135639 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.4937. Min Act: -0.1666

Data Index: 43569 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.4937. Min Act: -0.1699

Data Index: 48295 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.4937. Min Act: -0.1698

Data Index: 193498 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.4937. Min Act: -0.1693

Data Index: 603189 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.4937. Min Act: -0.1640

Data Index: 210504 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.5249. Min Act: -0.1612

Data Index: 304844 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.4624. Min Act: -0.1680

Data Index: 814898 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.4624. Min Act: -0.1651

Data Index: 497262 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.4312. Min Act: -0.1700

Data Index: 902676 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 5.8062. Min Range: -5.8062

Max Act: 5.4937. Min Act: -0.1700

Data Index: 691953 (C4 (Web Text))

Max Activating Token Index: 165