Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 569 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.5114. Min Act: -0.1700
Data Index: 7744106 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.5114. Min Act: -0.1700
Data Index: 7922324 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.5114. Min Act: -0.1700
Data Index: 1178687 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.4489. Min Act: -0.1700
Data Index: 1032157 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.4176. Min Act: -0.1700
Data Index: 5564574 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.3551. Min Act: -0.1700
Data Index: 4071640 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.3239. Min Act: -0.1700
Data Index: 4636600 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.2926. Min Act: -0.1700
Data Index: 5307059 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.2926. Min Act: -0.1700
Data Index: 4582328 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.2926. Min Act: -0.1700
Data Index: 4009354 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.2926. Min Act: -0.1700
Data Index: 253392 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.2614. Min Act: -0.1700
Data Index: 3944228 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.2301. Min Act: -0.1700
Data Index: 922610 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.1989. Min Act: -0.1700
Data Index: 6367271 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.1989. Min Act: -0.1700
Data Index: 7626364 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.1989. Min Act: -0.1700
Data Index: 2324636 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.1364. Min Act: -0.1700
Data Index: 302015 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.1676. Min Act: -0.1700
Data Index: 6603564 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.1364. Min Act: -0.1700
Data Index: 3481322 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5114. Min Range: -6.5114
Max Act: 6.1051. Min Act: -0.1700
Data Index: 885886 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19