Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1887 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.9721. Min Act: -0.1700
Data Index: 2178965 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.9096. Min Act: -0.1700
Data Index: 3613037 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.4096. Min Act: -0.1700
Data Index: 2585860 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.4096. Min Act: -0.1700
Data Index: 2220816 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.3471. Min Act: -0.1700
Data Index: 5413402 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.2846. Min Act: -0.1700
Data Index: 4009570 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.2221. Min Act: -0.1700
Data Index: 2897830 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.3471. Min Act: -0.1700
Data Index: 4899518 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.2221. Min Act: -0.1700
Data Index: 6484195 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.0971. Min Act: -0.1700
Data Index: 6932004 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.0346. Min Act: -0.1700
Data Index: 4240780 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9721. Min Range: -10.9721
Max Act: 10.0346. Min Act: -0.1700
Data Index: 152928 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9721. Min Range: -10.9721
Max Act: 9.9721. Min Act: -0.1700
Data Index: 3978689 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9721. Min Range: -10.9721
Max Act: 9.9721. Min Act: -0.1700
Data Index: 8748084 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9721. Min Range: -10.9721
Max Act: 9.9721. Min Act: -0.1700
Data Index: 5931993 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9721. Min Range: -10.9721
Max Act: 9.9721. Min Act: -0.1700
Data Index: 3767865 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9721. Min Range: -10.9721
Max Act: 9.9096. Min Act: -0.1700
Data Index: 7904650 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9721. Min Range: -10.9721
Max Act: 9.8471. Min Act: -0.1700
Data Index: 4612681 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9721. Min Range: -10.9721
Max Act: 9.8471. Min Act: -0.1700
Data Index: 1048128 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9721. Min Range: -10.9721
Max Act: 9.8471. Min Act: -0.1700
Data Index: 4448507 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19