Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.4012. Min Act: -0.1700
Data Index: 5084642 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.4012. Min Act: -0.1700
Data Index: 7938272 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.3387. Min Act: -0.1700
Data Index: 2653149 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.3387. Min Act: -0.1700
Data Index: 2350471 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.3387. Min Act: -0.1700
Data Index: 6913699 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.2762. Min Act: -0.1700
Data Index: 7785266 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.2762. Min Act: -0.1700
Data Index: 6859671 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.2137. Min Act: -0.1700
Data Index: 7001399 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.2137. Min Act: -0.1700
Data Index: 6383009 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.2137. Min Act: -0.1700
Data Index: 2023763 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.1512. Min Act: -0.1700
Data Index: 1494174 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.2137. Min Act: -0.1700
Data Index: 215286 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.1824. Min Act: -0.1700
Data Index: 8519785 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.1512. Min Act: -0.1700
Data Index: 4922452 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.1512. Min Act: -0.1700
Data Index: 6546577 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.1199. Min Act: -0.1700
Data Index: 5343901 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.1512. Min Act: -0.1700
Data Index: 3840463 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.1199. Min Act: -0.1700
Data Index: 922928 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.1199. Min Act: -0.1700
Data Index: 75349 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4012. Min Range: -7.4012
Max Act: 7.0887. Min Act: -0.1700
Data Index: 8026556 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19