Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6359 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.8431. Min Act: -0.1699
Data Index: 5109203 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.7181. Min Act: -0.1700
Data Index: 3899557 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.4681. Min Act: -0.1700
Data Index: 383364 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.4056. Min Act: -0.1700
Data Index: 3458216 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.4056. Min Act: -0.1700
Data Index: 8278209 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.3431. Min Act: -0.1700
Data Index: 6224605 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.2806. Min Act: -0.1700
Data Index: 4864808 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.2806. Min Act: -0.1698
Data Index: 4869754 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.1556. Min Act: -0.1694
Data Index: 4862192 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.0306. Min Act: -0.1699
Data Index: 601004 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.0306. Min Act: -0.1693
Data Index: 1659623 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.0306. Min Act: -0.1700
Data Index: 2661765 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.0306. Min Act: -0.1696
Data Index: 194416 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8431. Min Range: -12.8431
Max Act: 12.0931. Min Act: -0.1698
Data Index: 6390753 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8431. Min Range: -12.8431
Max Act: 11.9056. Min Act: -0.1698
Data Index: 8807342 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8431. Min Range: -12.8431
Max Act: 11.9056. Min Act: -0.1700
Data Index: 451558 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8431. Min Range: -12.8431
Max Act: 11.9681. Min Act: -0.1699
Data Index: 8542289 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8431. Min Range: -12.8431
Max Act: 11.8431. Min Act: -0.1700
Data Index: 4328903 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8431. Min Range: -12.8431
Max Act: 11.8431. Min Act: -0.1700
Data Index: 1091939 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8431. Min Range: -12.8431
Max Act: 11.8431. Min Act: -0.1635
Data Index: 2083187 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19