Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3880 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2975. Min Range: -6.2975
Max Act: 6.2975. Min Act: -0.1700
Data Index: 2921909 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2975. Min Range: -6.2975
Max Act: 6.0475. Min Act: -0.1700
Data Index: 8067791 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.9850. Min Act: -0.1700
Data Index: 8067792 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.9850. Min Act: -0.1700
Data Index: 5873977 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.9538. Min Act: -0.1700
Data Index: 3119183 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.8913. Min Act: -0.1700
Data Index: 6438356 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.8288. Min Act: -0.1700
Data Index: 1647994 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.7350. Min Act: -0.1700
Data Index: 4029989 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.7038. Min Act: -0.1700
Data Index: 518708 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.7038. Min Act: -0.1700
Data Index: 2326989 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.7038. Min Act: -0.1700
Data Index: 3250251 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.7038. Min Act: -0.1700
Data Index: 7731848 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.6413. Min Act: -0.1700
Data Index: 4058276 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.6413. Min Act: -0.1700
Data Index: 4437765 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.6413. Min Act: -0.1700
Data Index: 1038779 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.6413. Min Act: -0.1700
Data Index: 3125290 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.5475. Min Act: -0.1700
Data Index: 2851286 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.5788. Min Act: -0.1700
Data Index: 6903400 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.5788. Min Act: -0.1700
Data Index: 5074874 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2975. Min Range: -6.2975
Max Act: 5.5163. Min Act: -0.1700
Data Index: 7995906 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19