Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4812 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5913. Min Range: -7.5913
Max Act: 7.5913. Min Act: -0.1700
Data Index: 4514242 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5913. Min Range: -7.5913
Max Act: 7.0913. Min Act: -0.1700
Data Index: 6613852 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5913. Min Range: -7.5913
Max Act: 7.0913. Min Act: -0.1700
Data Index: 1879110 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.9976. Min Act: -0.1700
Data Index: 6330041 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.9663. Min Act: -0.1700
Data Index: 8417966 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.9038. Min Act: -0.1700
Data Index: 497416 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.9038. Min Act: -0.1700
Data Index: 3284334 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.8726. Min Act: -0.1700
Data Index: 5663474 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.8413. Min Act: -0.1700
Data Index: 4193278 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.8413. Min Act: -0.1700
Data Index: 604799 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.8413. Min Act: -0.1700
Data Index: 1248755 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.8726. Min Act: -0.1700
Data Index: 500636 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.7476. Min Act: -0.1700
Data Index: 7863377 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.6851. Min Act: -0.1700
Data Index: 1547255 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.7163. Min Act: -0.1700
Data Index: 3896310 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.7163. Min Act: -0.1700
Data Index: 5021219 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.6851. Min Act: -0.1700
Data Index: 8087603 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.6851. Min Act: -0.1700
Data Index: 2043433 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.6538. Min Act: -0.1700
Data Index: 6170988 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5913. Min Range: -7.5913
Max Act: 6.6226. Min Act: -0.1700
Data Index: 1690704 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19