Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2008. Min Range: -5.2008
Max Act: 5.2008. Min Act: -0.1700
Data Index: 209930 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2008. Min Range: -5.2008
Max Act: 5.0133. Min Act: -0.1700
Data Index: 937881 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.9820. Min Act: -0.1700
Data Index: 4138147 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.9820. Min Act: -0.1700
Data Index: 5804486 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.9195. Min Act: -0.1700
Data Index: 7057245 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.9508. Min Act: -0.1700
Data Index: 1617799 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.9195. Min Act: -0.1700
Data Index: 7924206 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8883. Min Act: -0.1700
Data Index: 402264 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8883. Min Act: -0.1700
Data Index: 8709927 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8570. Min Act: -0.1700
Data Index: 7285358 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8570. Min Act: -0.1700
Data Index: 8399319 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8883. Min Act: -0.1700
Data Index: 6131165 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8883. Min Act: -0.1700
Data Index: 6094276 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8570. Min Act: -0.1700
Data Index: 6877112 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.7945. Min Act: -0.1700
Data Index: 1352173 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8258. Min Act: -0.1700
Data Index: 2344840 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8258. Min Act: -0.1700
Data Index: 4759831 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8258. Min Act: -0.1700
Data Index: 7266579 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8258. Min Act: -0.1700
Data Index: 300672 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2008. Min Range: -5.2008
Max Act: 4.8258. Min Act: -0.1700
Data Index: 6825827 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19