Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1900 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.6188. Min Act: -0.1700
Data Index: 8524948 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.4313. Min Act: -0.1700
Data Index: 4669669 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.4001. Min Act: -0.1700
Data Index: 7941231 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.3688. Min Act: -0.1700
Data Index: 7890382 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.3376. Min Act: -0.1700
Data Index: 8061075 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.3063. Min Act: -0.1700
Data Index: 8106392 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.2126. Min Act: -0.1700
Data Index: 4917901 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.1813. Min Act: -0.1700
Data Index: 2542820 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.1813. Min Act: -0.1700
Data Index: 964277 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.1501. Min Act: -0.1700
Data Index: 5120931 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.1501. Min Act: -0.1700
Data Index: 1064574 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.1501. Min Act: -0.1700
Data Index: 7326788 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.1188. Min Act: -0.1700
Data Index: 1790132 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.1501. Min Act: -0.1700
Data Index: 7574824 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.0876. Min Act: -0.1700
Data Index: 7776548 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.1188. Min Act: -0.1700
Data Index: 3051731 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.1188. Min Act: -0.1700
Data Index: 846034 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.1188. Min Act: -0.1700
Data Index: 6158198 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.0876. Min Act: -0.1700
Data Index: 2453860 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6188. Min Range: -6.6188
Max Act: 6.0876. Min Act: -0.1700
Data Index: 7765525 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19