Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.8811. Min Act: -0.1700
Data Index: 7492962 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.8498. Min Act: -0.1700
Data Index: 2051231 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.7873. Min Act: -0.1700
Data Index: 2369480 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.7561. Min Act: -0.1700
Data Index: 170792 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.6623. Min Act: -0.1700
Data Index: 5600745 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.6936. Min Act: -0.1700
Data Index: 5375391 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.6311. Min Act: -0.1700
Data Index: 8225790 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.6623. Min Act: -0.1700
Data Index: 4030510 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.6311. Min Act: -0.1700
Data Index: 5384688 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.6311. Min Act: -0.1700
Data Index: 3552657 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.5686. Min Act: -0.1700
Data Index: 4376758 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.5686. Min Act: -0.1700
Data Index: 7835258 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.5686. Min Act: -0.1700
Data Index: 8428967 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.5686. Min Act: -0.1700
Data Index: 4126327 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.5061. Min Act: -0.1700
Data Index: 5358599 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.5061. Min Act: -0.1700
Data Index: 4143262 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.5061. Min Act: -0.1700
Data Index: 3111067 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.4748. Min Act: -0.1700
Data Index: 4842086 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.5061. Min Act: -0.1700
Data Index: 6705060 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8811. Min Range: -5.8811
Max Act: 5.5061. Min Act: -0.1700
Data Index: 3383302 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19