Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2842 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.9871. Min Act: -0.1700
Data Index: 1887853 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.9246. Min Act: -0.1700
Data Index: 3440861 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.9246. Min Act: -0.1700
Data Index: 8589268 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.8621. Min Act: -0.1700
Data Index: 6773845 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.7684. Min Act: -0.1700
Data Index: 4387870 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.7059. Min Act: -0.1700
Data Index: 624886 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.6746. Min Act: -0.1700
Data Index: 2360191 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.6121. Min Act: -0.1700
Data Index: 8649847 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.5184. Min Act: -0.1700
Data Index: 2748335 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.3934. Min Act: -0.1700
Data Index: 7201550 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.3934. Min Act: -0.1700
Data Index: 8612911 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.2684. Min Act: -0.1700
Data Index: 589617 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.2059. Min Act: -0.1700
Data Index: 3019426 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.1746. Min Act: -0.1700
Data Index: 4944565 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.1434. Min Act: -0.1700
Data Index: 6552210 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.1434. Min Act: -0.1700
Data Index: 4155701 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.1121. Min Act: -0.1700
Data Index: 3856813 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.1121. Min Act: -0.1700
Data Index: 2647660 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.0496. Min Act: -0.1700
Data Index: 8580960 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9871. Min Range: -5.9871
Max Act: 5.0184. Min Act: -0.1700
Data Index: 7487475 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19