Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5722 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0008. Min Range: -8.0008
Max Act: 8.0008. Min Act: -0.1700
Data Index: 6722065 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0008. Min Range: -8.0008
Max Act: 8.0008. Min Act: -0.1700
Data Index: 5328093 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.9071. Min Act: -0.1700
Data Index: 4141650 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.8758. Min Act: -0.1700
Data Index: 8002452 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.8133. Min Act: -0.1700
Data Index: 7751844 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.7508. Min Act: -0.1700
Data Index: 7111955 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.7508. Min Act: -0.1700
Data Index: 8666129 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.7196. Min Act: -0.1700
Data Index: 7736449 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.6883. Min Act: -0.1700
Data Index: 2633074 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.6883. Min Act: -0.1700
Data Index: 3691293 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.6571. Min Act: -0.1700
Data Index: 7900491 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.5946. Min Act: -0.1700
Data Index: 2975783 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.5946. Min Act: -0.1700
Data Index: 7802034 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.5946. Min Act: -0.1700
Data Index: 4064895 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.5633. Min Act: -0.1700
Data Index: 8373122 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.5633. Min Act: -0.1700
Data Index: 510061 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.5321. Min Act: -0.1700
Data Index: 7996022 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.5321. Min Act: -0.1700
Data Index: 4005587 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.5008. Min Act: -0.1700
Data Index: 2871970 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0008. Min Range: -8.0008
Max Act: 7.5008. Min Act: -0.1700
Data Index: 711414 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19