Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4331 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2988. Min Range: -6.2988
Max Act: 6.2988. Min Act: -0.1700
Data Index: 3838734 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2988. Min Range: -6.2988
Max Act: 6.2988. Min Act: -0.1700
Data Index: 4056994 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2988. Min Range: -6.2988
Max Act: 6.2676. Min Act: -0.1700
Data Index: 4658583 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2988. Min Range: -6.2988
Max Act: 6.2051. Min Act: -0.1700
Data Index: 5680695 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2988. Min Range: -6.2988
Max Act: 6.0488. Min Act: -0.1700
Data Index: 8239530 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2988. Min Range: -6.2988
Max Act: 6.0176. Min Act: -0.1700
Data Index: 4099759 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.9863. Min Act: -0.1700
Data Index: 2286820 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.9863. Min Act: -0.1700
Data Index: 1872968 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.9551. Min Act: -0.1698
Data Index: 3331946 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.9238. Min Act: -0.1700
Data Index: 1144364 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.8926. Min Act: -0.1700
Data Index: 3288584 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.8926. Min Act: -0.1700
Data Index: 1959035 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.8926. Min Act: -0.1700
Data Index: 3624499 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.8926. Min Act: -0.1700
Data Index: 4597927 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.8613. Min Act: -0.1700
Data Index: 4764898 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.8301. Min Act: -0.1700
Data Index: 5912536 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.8301. Min Act: -0.1700
Data Index: 2856867 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.8301. Min Act: -0.1700
Data Index: 1959037 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.7988. Min Act: -0.1700
Data Index: 2932599 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2988. Min Range: -6.2988
Max Act: 5.7988. Min Act: -0.1700
Data Index: 4469294 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19