Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.9562. Min Act: -0.1700
Data Index: 4693991 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.8625. Min Act: -0.1700
Data Index: 94169 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.8625. Min Act: -0.1700
Data Index: 6286534 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.8000. Min Act: -0.1700
Data Index: 4444206 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.7062. Min Act: -0.1700
Data Index: 1191146 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.7062. Min Act: -0.1700
Data Index: 8019300 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.6750. Min Act: -0.1700
Data Index: 4663643 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.7062. Min Act: -0.1700
Data Index: 6135583 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.7062. Min Act: -0.1700
Data Index: 2494988 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.7062. Min Act: -0.1700
Data Index: 1456045 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.6437. Min Act: -0.1700
Data Index: 3637493 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.6125. Min Act: -0.1700
Data Index: 1344616 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.6125. Min Act: -0.1700
Data Index: 948018 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.5812. Min Act: -0.1700
Data Index: 5746912 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.5812. Min Act: -0.1700
Data Index: 1042580 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.5812. Min Act: -0.1700
Data Index: 5321763 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.5812. Min Act: -0.1700
Data Index: 1098892 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.5500. Min Act: -0.1700
Data Index: 4609346 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.5500. Min Act: -0.1700
Data Index: 2778148 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9562. Min Range: -5.9562
Max Act: 5.5500. Min Act: -0.1700
Data Index: 1566787 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19