Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.7752. Min Act: -0.1700
Data Index: 6578941 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.4315. Min Act: -0.1700
Data Index: 6726719 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.3690. Min Act: -0.1700
Data Index: 1279519 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.3065. Min Act: -0.1700
Data Index: 2442250 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.2440. Min Act: -0.1700
Data Index: 8011998 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.2752. Min Act: -0.1700
Data Index: 1605610 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.2440. Min Act: -0.1700
Data Index: 1774384 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.2127. Min Act: -0.1700
Data Index: 2996000 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.1502. Min Act: -0.1700
Data Index: 7491725 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.1502. Min Act: -0.1700
Data Index: 4317661 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.1190. Min Act: -0.1700
Data Index: 2644175 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.1502. Min Act: -0.1700
Data Index: 1691914 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.1190. Min Act: -0.1700
Data Index: 4634719 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.0565. Min Act: -0.1700
Data Index: 916668 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.0252. Min Act: -0.1700
Data Index: 1588102 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.0252. Min Act: -0.1700
Data Index: 8217156 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.0252. Min Act: -0.1700
Data Index: 7131234 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.0252. Min Act: -0.1700
Data Index: 5847278 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.0252. Min Act: -0.1700
Data Index: 88954 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7752. Min Range: -6.7752
Max Act: 6.0565. Min Act: -0.1700
Data Index: 4713508 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19