Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.9900. Min Act: -0.1700
Data Index: 3384777 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.8025. Min Act: -0.1700
Data Index: 3518176 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.7713. Min Act: -0.1700
Data Index: 8684578 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.6775. Min Act: -0.1700
Data Index: 3623896 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.6775. Min Act: -0.1700
Data Index: 2406332 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.6463. Min Act: -0.1700
Data Index: 1731990 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.6150. Min Act: -0.1700
Data Index: 3590944 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.6150. Min Act: -0.1700
Data Index: 7914598 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.6150. Min Act: -0.1700
Data Index: 2541069 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.6150. Min Act: -0.1700
Data Index: 6844377 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.5838. Min Act: -0.1700
Data Index: 6368126 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.5838. Min Act: -0.1700
Data Index: 1211261 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.5838. Min Act: -0.1700
Data Index: 937019 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.5838. Min Act: -0.1700
Data Index: 1653350 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.5525. Min Act: -0.1700
Data Index: 3698233 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.5525. Min Act: -0.1700
Data Index: 2021940 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.5838. Min Act: -0.1700
Data Index: 2181971 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.5525. Min Act: -0.1700
Data Index: 5600281 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.5525. Min Act: -0.1700
Data Index: 820851 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9900. Min Range: -5.9900
Max Act: 5.5525. Min Act: -0.1700
Data Index: 2218862 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19