Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4880 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2751. Min Range: -8.2751
Max Act: 8.2751. Min Act: -0.1700
Data Index: 1186099 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2751. Min Range: -8.2751
Max Act: 7.4626. Min Act: -0.1700
Data Index: 6072673 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2751. Min Range: -8.2751
Max Act: 7.3689. Min Act: -0.1700
Data Index: 4167304 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2751. Min Range: -8.2751
Max Act: 7.1814. Min Act: -0.1700
Data Index: 770615 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2751. Min Range: -8.2751
Max Act: 7.0876. Min Act: -0.1700
Data Index: 4464689 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2751. Min Range: -8.2751
Max Act: 7.0564. Min Act: -0.1700
Data Index: 4163432 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.9001. Min Act: -0.1700
Data Index: 5397410 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.8689. Min Act: -0.1700
Data Index: 7405611 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.8689. Min Act: -0.1700
Data Index: 3443327 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.8376. Min Act: -0.1700
Data Index: 3285455 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.8064. Min Act: -0.1700
Data Index: 3418424 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.7439. Min Act: -0.1700
Data Index: 2433770 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.7126. Min Act: -0.1700
Data Index: 5453540 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.6814. Min Act: -0.1700
Data Index: 3716321 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.6814. Min Act: -0.1700
Data Index: 8502763 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.6501. Min Act: -0.1700
Data Index: 4856702 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.6501. Min Act: -0.1700
Data Index: 5461276 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.6501. Min Act: -0.1700
Data Index: 4173335 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.5876. Min Act: -0.1700
Data Index: 3120832 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2751. Min Range: -8.2751
Max Act: 6.5876. Min Act: -0.1700
Data Index: 229119 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19