Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6329 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.2837. Min Act: -0.1700
Data Index: 3164218 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.3150. Min Act: -0.1700
Data Index: 1510737 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.2212. Min Act: -0.1700
Data Index: 8144001 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.2212. Min Act: -0.1700
Data Index: 7791299 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.1900. Min Act: -0.1700
Data Index: 4967194 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.2212. Min Act: -0.1700
Data Index: 938283 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.1587. Min Act: -0.1700
Data Index: 6029643 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.1275. Min Act: -0.1700
Data Index: 7595608 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.1275. Min Act: -0.1700
Data Index: 6952240 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0962. Min Act: -0.1700
Data Index: 2328134 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.1275. Min Act: -0.1700
Data Index: 1782984 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0962. Min Act: -0.1700
Data Index: 8190329 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.1275. Min Act: -0.1700
Data Index: 7841053 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0650. Min Act: -0.1700
Data Index: 3234025 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0962. Min Act: -0.1700
Data Index: 7355041 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0962. Min Act: -0.1700
Data Index: 2866970 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0650. Min Act: -0.1700
Data Index: 1663924 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0650. Min Act: -0.1700
Data Index: 270875 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0650. Min Act: -0.1700
Data Index: 6006918 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0650. Min Act: -0.1700
Data Index: 527568 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19